The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill fetches and processes untrusted external data from App Store and Google Play listing pages via WebFetch in SKILL.md. 1. Ingestion points: Data is retrieved from apps.apple.com and play.google.com during the Phase 1 fetch step. 2. Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing the fetched metadata. 3. Capability inventory: The skill uses WebFetch for data ingestion but does not include any file-write, subprocess, or dynamic execution capabilities in its defined instructions. 4. Sanitization: There are no instructions to sanitize, escape, or filter the external content before it is analyzed by the agent.

aso-audit