Skills
Navigate
skills/ffroliva/gflow-cli/issue-assessment/Gen Agent Trust Hub

issue-assessment

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub issues, creating a surface for indirect prompt injection.
  • Ingestion points: The skill reads external content in the Protocol section of SKILL.md using gh issue view <N> --json title,body,comments,labels,author,state.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for the ingested issue content.
  • Capability inventory: The skill uses gh CLI commands (gh issue view, gh pr list, gh issue list) and repository file reading in SKILL.md.
  • Sanitization: No sanitization or filtering of the issue body or comments is mentioned before processing.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the GitHub CLI.
  • Evidence: gh issue view, gh pr list, and gh issue list are used in SKILL.md to gather context during the triage process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 08:25 AM