replica-launch
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python linter script,
listing.py, to validate generated App Store and Google Play metadata. The script uses only standard Python libraries and performs local text analysis without network access or privileged operations.- [INDIRECT_PROMPT_INJECTION]: The skill processes external data fromfeedback.mdandreplica/fixes.md. While these sources could contain untrusted content such as app reviews, the skill includes explicit instructions to paraphrase content and avoid direct quotes, providing a boundary against potential injection attempts in the source data.
Audit Metadata