The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external code files and repository diffs, which are untrusted data sources.
Ingestion points: Source files and git diffs are fed to the agent for review as described in references/comment-sicko-prompt.md.
Boundary markers: The instructions do not define specific delimiters or "ignore" warnings to prevent instructions embedded in comments from influencing the agent.
Capability inventory: The skill is strictly limited to read-only reporting and is explicitly prohibited from writing application code or using network tools as per references/comment-sicko-prompt.md.
Sanitization: No specific sanitization or escaping of the ingested code content is mentioned.
[SAFE]: The skill incorporates strong defensive constraints by explicitly disabling network connectors and enforcing a read-only runtime posture in references/comment-sicko-prompt.md.

no-comments