aso
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from third-party app store listings, creating a surface for indirect prompt injection attacks where malicious instructions could be embedded in app descriptions or reviews.
- Ingestion points: External metadata including titles, descriptions, and user reviews are retrieved using the WebFetch tool as described in Phase 1 of SKILL.md.
- Boundary markers: The instructions lack specific guidance for the agent to use delimiters or 'ignore embedded instructions' warnings when processing the scraped content, increasing the risk that the agent might follow instructions found within a listing's description.
- Capability inventory: The skill utilizes WebFetch and Screenshot tools and produces a detailed report. It does not have access to high-risk capabilities such as arbitrary shell execution, file-system writes, or network exfiltration of local secrets.
- Sanitization: There are no explicit requirements for the agent to sanitize or validate the content of the retrieved listing data before performing the audit analysis.
Audit Metadata