update-ticket
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Jira/GitHub tickets and local project files, creating a surface for indirect prompt injection.
- Ingestion points: File reads of .agents/projects/ artifacts and external ticket content (SKILL.md, Step 1).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present.
- Capability inventory: Access to read/write local project files and update external trackers via network tools (SKILL.md, Steps 4 and 5).
- Sanitization: The skill does not explicitly sanitize data from external sources before processing.
- Mitigation: Requiring explicit user approval for the drafted content before posting is a robust defense against automated exfiltration or unauthorized actions.
Audit Metadata