The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute well-known security scanning utilities including semgrep, bandit, gitleaks, npm audit, and trivy. These operations are consistent with the skill's stated purpose of conducting security audits.
[PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection. Ingestion points: Untrusted local files and directory structures accessed via Read, Grep, Glob, and Bash tools. Boundary markers: None identified to delimit file content from analysis instructions. Capability inventory: The skill has the ability to execute shell commands and read files. Sanitization: There is no evidence of sanitization or filtering of the processed data to prevent malicious payloads from influencing the agent's summary or recommendations.

security-reviewer