The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted source code from various projects, which provides a surface for indirect prompt injection attacks where malicious code comments or strings could attempt to influence the agent's behavior.
Ingestion points: Source code files across multiple languages (Python, JavaScript, Go, etc.) as detailed in references/detailed-guide.md.
Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potential instructions embedded within the analyzed code.
Capability inventory: The agent is instructed to execute shell commands (pip, npm, semgrep, bandit) and write files (bandit-report.json, eslint-security.json).
Sanitization: No sanitization steps are defined for the input code before analysis.
[COMMAND_EXECUTION]: The skill requires the agent to execute shell commands to install security tools and perform scans.
Evidence in references/detailed-guide.md: pip install bandit, npm install eslint, semgrep scan --config=auto, mvn spotbugs:check, gosec -fmt=json ....
[EXTERNAL_DOWNLOADS]: The skill fetches security scanning tools from well-known package registries.
Evidence in references/detailed-guide.md: Installation of bandit and semgrep from PyPI, and eslint plugins from the npm registry.

security-scanning-security-sast