gadd-close
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill ingests data from local files such as
ledger.ymlandverification.md, which constitutes an indirect prompt injection surface. This is a low-risk surface associated with the skill's primary workflow. - Ingestion points:
ledger.yml,verification.md, andgadd/config.yml(SKILL.md). - Boundary markers: None identified.
- Capability inventory: Filesystem read/write operations for ledger management; network API calls to external trackers such as GitHub, Jira, and Linear (SKILL.md).
- Sanitization: No explicit validation or sanitization of input file text is specified beyond checking status fields.\n- [EXTERNAL_DOWNLOADS]: The skill communicates with well-known external project management services. All such network operations are restricted to status synchronization and require explicit human confirmation for any mutations, aligning with safe operational practices.
Audit Metadata