skill-triager

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches JSON data from the author's official GitHub repository and API to verify skill indexing and availability during the triaging process.
  • [COMMAND_EXECUTION]: Extensively uses the GitHub CLI (gh) to read and update issue states, fetch file contents, post comments, and trigger repository dispatches for CI/CD automation. It also employs python3 to parse downloaded JSON data and npx to facilitate local skill installation for developers.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub issue titles and bodies, which are used to generate review packets and construct command-line arguments. * Ingestion points: Issue bodies and specification markdown files retrieved from the peter-tu-zynkr/zynkr-skill-idea repository (referenced in SKILL.md). * Boundary markers: Absent. The instructions do not define specific delimiters or warnings to ignore potential instructions embedded within the issue data. * Capability inventory: Shell execution via gh, curl, and python3, firing of repository dispatches, and interactions with Google Drive and Sheets APIs (referenced in SKILL.md). * Sanitization: No explicit sanitization or validation of the ingested issue content is performed before interpolation into administrative commands and review displays.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:31 PM
Security Audit — agent-trust-hub — skill-triager