triage-issue-reports
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (Slack reports) which may contain malicious instructions intended to influence the agent's triaging behavior or the content of created tracker issues.
- Ingestion points: Section 2 of
SKILL.mddetails the ingestion of reporter wording, app builds, error text, logs, and attachments (screenshots/videos). - Boundary markers: The skill does not define specific delimiters or "ignore instructions" tags when processing reporter quotes or log contents.
- Capability inventory: The skill has the capability to create and update issues in external trackers (e.g., Linear, GitHub) and post verdicts back to Slack threads (
SKILL.mdSections 6 and 9). - Sanitization: While the skill instructs the agent to label hypotheses and use plain titles, there is no explicit instruction to sanitize or escape user-provided content before it is interpolated into the tracker adapter or Slack verdict post.
Audit Metadata