app-store-changelog
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests git commit messages and file lists which are untrusted data that could contain malicious instructions.\n
- Ingestion points: Output from scripts/collect_release_changes.sh (referenced in SKILL.md).\n
- Boundary markers: The skill provides instructions to filter changes but lacks specific delimiters or guardrails to prevent the agent from obeying instructions hidden within commit messages.\n
- Capability inventory: Execution of local shell scripts.\n
- Sanitization: No sanitization or validation of the ingested git data is mentioned.\n- [COMMAND_EXECUTION]: The skill relies on the execution of a local script scripts/collect_release_changes.sh to function. While the script is local to the repository, its content was not provided for security verification.
Audit Metadata