list-issues-pr-pulse

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill retrieves data from GitHub issues and pull requests, which may contain attacker-controlled text that could influence agent behavior via indirect prompt injection.
  • Ingestion points: Data enters the agent context through gh issue list and gh pr list command outputs as defined in SKILL.md.
  • Boundary markers: The current output format does not use specific delimiters or instructions to ignore instructions embedded within the retrieved issue or PR titles.
  • Capability inventory: The skill utilizes subprocess execution via the GitHub CLI (gh).
  • Sanitization: The skill uses jq to format JSON into text, which provides structure but does not filter the content of the fields for malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 01:15 PM
Security Audit — agent-trust-hub — list-issues-pr-pulse