agency-app-store-optimizer
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing untrusted external data, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: The agent is instructed to research app store landscapes, analyze competitor positioning, and monitor user reviews and ratings in SKILL.md.
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat external content as untrusted or to ignore embedded instructions within that content.
- Capability inventory: The skill defines a persona and strategy frameworks but does not contain active tool definitions, script execution logic, or automated network/file-writing capabilities within the provided file.
- Sanitization: No specific sanitization or filtering of external content is mentioned.
Audit Metadata