triage-issue-reports
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it ingests and processes untrusted data from Slack reports.
- Ingestion points: The agent captures reporter wording, error text, logs, and attachments from Slack threads (SKILL.md, Section 2).
- Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands when processing these untrusted inputs.
- Capability inventory: The skill can post messages to Slack threads and create or update issues in external trackers like Linear or GitHub (SKILL.md, Sections 6 and 9).
- Sanitization: There is no mention of input sanitization or filtering for the reporter-supplied content before it is used for triage decisions.- [SAFE]: The skill implements several security best practices. It freezes source coordinates to prevent message spoofing, enforces read-only access for delegated workers to prevent credential leakage, and includes a fail-closed mechanism for tracker issue creation if Slack communication fails (SKILL.md, Sections 1 and 6).
Audit Metadata