The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes external content from git diffs and repository files, creating a surface where malicious instructions embedded in code could influence the agent.
Ingestion points: The agent ingests untrusted data from git diff output and file content via Read and Glob tools as specified in SKILL.md.
Boundary markers: The skill does not implement boundary markers or instructions to isolate analyzed code from the agent's command context.
Capability inventory: The skill possesses access to Bash (restricted to git commands), Read, Grep, and Glob tools (SKILL.md).
Sanitization: The skill lacks logic to sanitize or validate the content of git diffs before processing them.

grill-me