gavel
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from potentially untrusted external sources, which could contain malicious instructions intended to manipulate the agent's behavior during triage or execution.
- Ingestion points: The agent sweeps for items in conversation history, issue trackers (tickets), project plans, specifications, ledgers, and findings from audits or reviews (SKILL.md, Sections 1 & 2).
- Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted external data from the agent's internal instructional logic or to warn the agent to ignore embedded instructions.
- Capability inventory: The agent has the authority to "do it directly" for items categorized as clear, which includes mechanical fixes, confirmed bug fixes, dispatching tasks, and updating tickets or documentation. It also records rulings into ADRs, specs, or docs (SKILL.md, Sections 3, 6, & 8).
- Sanitization: The skill lacks explicit sanitization or validation steps for the content retrieved from external trackers and documents before it is used to determine actions or recommendations.
Audit Metadata