cisco-ai-defense/skill-scanner

cisco-ai-defense/skill-scanner · .cursor/rules/codeguard-0-additional-cryptography.mdc · Additional Cryptography guidance

cisco-ai-defense/skill-scanner · .cursor/rules/codeguard-0-framework-and-languages.mdc · Framework & language security guides (Django/DRF, Laravel/Symfony/Rails, .NET, Java/JAAS, Node.js, PHP config)

cisco-ai-defense/skill-scanner · .cursor/rules/codeguard-0-iac-security.mdc · Infrastructure as Code Security

cisco-ai-defense/skill-scanner · .cursor/rules/codeguard-0-mobile-apps.mdc · Mobile app security (iOS/Android): storage, transport, code integrity, biometrics, permissions

cisco-ai-defense/skill-scanner · .cursor/rules/codeguard-0-supply-chain-security.mdc · Dependency & supply chain security (pinning, SBOM, provenance, integrity, private registries)

cisco-ai-defense/skill-scanner · .cursor/rules/codeguard-1-crypto-algorithms.mdc · Cryptographic Security Guidelines

cisco-ai-defense/skill-scanner · .cursor/rules/codeguard-1-digital-certificates.mdc · Certificate Best Practices

cisco-ai-defense/skill-scanner · .cursor/rules/codeguard-1-hardcoded-credentials.mdc · No Hardcoded Credentials

cisco-ai-defense/skill-scanner · .cursor/rules/no-cursor-co-author.mdc · Never add Cursor as a co-author in git commits

cisco-ai-defense/skill-scanner · evals/skills/autonomy-abuse/no-confirmation/SKILL.md · Direct the agent to act while bypassing user confirmation

cisco-ai-defense/skill-scanner · evals/skills/backdoor/magic-string-trigger/SKILL.md · Compile caller-provided source text into an executable code object

cisco-ai-defense/skill-scanner · evals/skills/behavioral-analysis/multi-file-exfiltration/SKILL.md · Send a diagnostic record over an explicitly external raw socket

cisco-ai-defense/skill-scanner · evals/skills/command-injection/eval-execution/SKILL.md · Compile a caller-provided expression into a Python code object

cisco-ai-defense/skill-scanner · evals/skills/data-exfiltration/config-tunnel-exfil/SKILL.md · Sync calendar events with an endpoint selected in configuration

cisco-ai-defense/skill-scanner · evals/skills/data-exfiltration/environment-dump/SKILL.md · Summarise a CSV file into row counts and the most common values per column

cisco-ai-defense/skill-scanner · evals/skills/data-exfiltration/environment-secrets/SKILL.md · Read a sensitive operating-system credential file for diagnostics

cisco-ai-defense/skill-scanner · evals/skills/hardcoded-secrets/stripe-key/SKILL.md · Demonstrate a credential-shaped payment key embedded in instructions

cisco-ai-defense/skill-scanner · evals/skills/harmful-content/explicit-ransomware-request/SKILL.md · Issue an explicit imperative request for a prohibited cyber-harm capability

cisco-ai-defense/skill-scanner · evals/skills/malware/ransomware-chain/SKILL.md · Demonstrate a multi-stage file encryption and extortion implementation

cisco-ai-defense/skill-scanner · evals/skills/obfuscation/base64-payload/SKILL.md · Transform an integer with XOR and compile caller-provided source

cisco-ai-defense/skill-scanner · evals/skills/path-traversal/file-reader/SKILL.md · Read a caller-selected path without confining it to a safe root

cisco-ai-defense/skill-scanner · evals/skills/policy-violation/missing-license/SKILL.md · Perform a benign transformation while omitting license metadata

cisco-ai-defense/skill-scanner · evals/skills/prompt-injection/jailbreak-override/SKILL.md · Conceal an agent action from the user who requested the task

cisco-ai-defense/skill-scanner · evals/skills/resource-exhaustion/infinite-loop/SKILL.md · Analyze an input repeatedly without a termination condition

cisco-ai-defense/skill-scanner · evals/skills/safe-skills-2/env-config-reader/SKILL.md · Read a small fixed set of environment variables the skill needs

cisco-ai-defense/skill-scanner · evals/skills/safe-skills-2/file-validator/SKILL.md · Validate a filename extension without opening any filesystem path

cisco-ai-defense/skill-scanner · evals/skills/safe-skills-2/registry-default-mirror/SKILL.md · Pin the npm registry to the public default and fetch published release notes

cisco-ai-defense/skill-scanner · evals/skills/safe-skills/simple-math/SKILL.md · Perform basic arithmetic using a direct operator implementation

cisco-ai-defense/skill-scanner · evals/skills/skill-discovery-abuse/keyword-stuffing/SKILL.md · Inflate skill discovery through repeated activation keywords

cisco-ai-defense/skill-scanner · evals/skills/social-engineering/vague-description/SKILL.md · Utility

cisco-ai-defense/skill-scanner · evals/skills/sql-injection/database-query/SKILL.md · Construct a database query by interpolating a caller-controlled identifier

cisco-ai-defense/skill-scanner · evals/skills/supply-chain-attack/registry-redirect-declared/SKILL.md · Bootstrap a development environment and set the npm registry to https://npm.artifacts-mirror.internal-corp.dev

cisco-ai-defense/skill-scanner · evals/skills/supply-chain-attack/registry-redirect/SKILL.md · Bootstrap a development environment and configure the corporate package mirror

cisco-ai-defense/skill-scanner · evals/skills/supply-chain-attack/unpinned-dependency/SKILL.md · Demonstrate a package dependency that is not locked to an exact version

cisco-ai-defense/skill-scanner · evals/skills/tool-chaining-abuse/attacker-forwarding/SKILL.md · Forward collected data to an explicitly attacker-controlled destination

cisco-ai-defense/skill-scanner · evals/skills/transitive-trust-abuse/external-instructions/SKILL.md · Delegate agent behavior to instructions obtained from an external page

cisco-ai-defense/skill-scanner · evals/skills/unauthorized-tool-use/remote-package-source/SKILL.md · Install a Python package directly from an untrusted remote archive

cisco-ai-defense/skill-scanner · evals/skills/unicode-steganography/encoded-tag/SKILL.md · Contain an encoded Unicode Tag Block marker used for hidden instructions

cisco-ai-defense/skill-scanner · evals/test_skills/malicious/ascii-smuggling/SKILL.md · Retrieves current weather conditions and forecasts for any location worldwide

cisco-ai-defense/skill-scanner · evals/test_skills/malicious/eicar-test/SKILL.md · Test skill containing EICAR test file for malware detection

cisco-ai-defense/skill-scanner · evals/test_skills/malicious/exfiltrator/SKILL.md · Analyzes data files

cisco-ai-defense/skill-scanner · evals/test_skills/malicious/flowise-cve-2025-59528/SKILL.md

cisco-ai-defense/skill-scanner · evals/test_skills/malicious/mcp-atlassian-cve-2026-27825/SKILL.md

cisco-ai-defense/skill-scanner · evals/test_skills/malicious/mcpwn-cve-2026-33032/SKILL.md

cisco-ai-defense/skill-scanner · evals/test_skills/malicious/prompt-injection/SKILL.md · A test skill with prompt injection patterns

cisco-ai-defense/skill-scanner · evals/test_skills/safe/atr-benign-control/SKILL.md

cisco-ai-defense/skill-scanner · evals/test_skills/safe/simple-formatter/SKILL.md · Formats text according to specified style guidelines. A clean example skill with no security issues.