plan-aso
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious instructions, obfuscation, or persistence mechanisms were found. The skill operates within a restricted 'plan-only' scope, requiring approval before any listing edits are made.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface typical of analysis tools that process external content.
- Ingestion points: The skill ingests untrusted data including app titles, descriptions, and user reviews from the App Store and Google Play (Phase 0 in SKILL.md).
- Boundary markers: There are no explicit delimiters defined to separate external app data from agent instructions.
- Capability inventory: The skill's primary capability is writing a report to
plan-aso.md. It does not utilize shell execution, network exfiltration, or privileged system access. - Sanitization: The skill does not specify sanitization for the gathered metadata, but its limited capability to execute instructions significantly reduces the risk of exploitation.
Audit Metadata