specrail-triage-issue

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (checks/github_issue_evidence.py and checks/route_gate.py) to gather evidence and perform triage routing based on GitHub issue data.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from GitHub issues.
  • Ingestion points: Untrusted content enters the agent context through the triage of GitHub issues (referenced in SKILL.md).
  • Boundary markers: The instructions lack explicit boundary markers or delimiters to differentiate between system instructions and content within the GitHub issues.
  • Capability inventory: The skill possesses the capability to execute shell commands (python3) and write files to the artifacts/triage/ directory.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the external content retrieved from the GitHub API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 09:48 AM
Security Audit — agent-trust-hub — specrail-triage-issue