triage
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple sources which can influence the agent's behavior during triage and reporting.
- Ingestion points: The skill reads external data including issue descriptions, comments, labels, reporter information, and local markdown files (Procedures step 1 and "A markdown ticket" section in SKILL.md).
- Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the ingested data before it is processed into triage notes or placeholders.
- Capability inventory: The skill has the capability to write comments, change issue states/labels, modify local files (e.g.,
.out-of-scope/*.md), and delete or archive local markdown files after promoting them to the tracker. - Sanitization: No sanitization or filtering of external content is mentioned before it is interpolated into the triage reports or system summaries.
Audit Metadata