improve-search-visibility-store-listing-audit
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and read content from external, public sources (Apple App Store and Google Play Store listings), which are attacker-controllable environments.
- Ingestion points: Public store listings accessed via host fetch or user-provided screenshots (SKILL.md, step 1).
- Boundary markers: The instructions do not specify delimiters or constraints to prevent the agent from being influenced by instructions embedded within the listing text.
- Capability inventory: The skill involves reading files and web content and writing reports; no high-risk capabilities like shell execution or persistent storage modifications were identified.
- Sanitization: No sanitization or validation of the fetched external text is described in the provided instructions.
Audit Metadata