The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from the local file system and external documentation, which could contain instructions designed to influence the agent's behavior during the audit process.
Ingestion points: The agent uses Read, Glob, and Grep to scan the repository and WebFetch to retrieve external documentation from serpapi.com.
Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate processed data from the agent's core instructions.
Capability inventory: The skill utilizes Write and Edit tools to record audit decisions and redacted evidence to the file system.
Sanitization: There are no explicit instructions for sanitizing or filtering the content fetched from external sources or read from the repository.

serpapi-prod-checklist