The Agent Skills Directory

[SAFE]: The skill's primary function is to perform a security audit on a codebase, including scanning for hardcoded secrets, personal information, and missing documentation. These operations are consistent with the tool's stated purpose.
[INDIRECT_PROMPT_INJECTION]: This skill presents an attack surface for indirect prompt injection because it is designed to read and process untrusted data from a repository's source files and metadata (Ingestion points: SKILL.md instructions to read all source files). There are no specific instructions for the agent to use boundary markers or to sanitize the content before processing (Boundary markers: absent; Sanitization: absent). While an attacker could place malicious instructions in the audited files to influence the agent's findings, the skill does not possess high-risk capabilities like network access, which limits the potential impact (Capability inventory: file system inspection, grep operations).

review