The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a variety of shell commands for project discovery and diagnostic purposes (e.g., git rev-parse, git ls-files, wc, npm audit, pip-audit, bandit). These operations are required for the skill's primary purpose of auditing a codebase.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the project being audited (source code, READMEs, etc.). Ingestion points: The skill reads project files, manifests, and git history across the repository (SKILL.md, Step 2, Step 4). Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded within the code being analyzed. Capability inventory: The agent has access to Bash for command execution and Write for generating the audit report. Sanitization: No specific content sanitization or validation is mentioned for the ingested source code.

code-analyzer