The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes project files and external web content to perform audits. This presents a surface for indirect prompt injection where malicious instructions inside reviewed documents could attempt to influence the agent.
Ingestion points: Processes local files via Read and Grep and external content via WebFetch and WebSearch in Step 1.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore commands found within the audited content.
Capability inventory: The skill has access to Bash, Write, and WebFetch tools.
Sanitization: No sanitization or validation of the ingested content is described in the workflow.

audit-legal