The Agent Skills Directory

[PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. * Ingestion points: The skill workflow relies on processing untrusted external code diffs and files. * Boundary markers: Absent; no specific delimiters or warnings are provided to the agent to ignore instructions embedded within the code samples being reviewed. * Capability inventory: None; the skill is purely instructional and lacks tools for shell execution, network access, or file system modifications. * Sanitization: Absent; no input validation or escaping mechanisms are defined for the data processed by the skill.

code-review