The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes untrusted data from the codebase and user-provided input.
Ingestion points: Reads local files using Read, Glob, and Grep tools and accepts a user-provided description argument in the SKILL.md instructions.
Boundary markers: Absent. The skill does not define specific delimiters or instructions to prevent the agent from obeying commands hidden within the code files or bug descriptions it analyzes.
Capability inventory: Utilizes Read, Glob, Grep, and Write tools to perform analysis and generate reports.
Sanitization: No sanitization, escaping, or validation of the ingested data is specified before the agent processes it for report generation.

bug-report