issue-troubleshooting

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a utility script scripts/find-polluter.sh designed to locate tests that cause filesystem pollution. This script executes npm test on local files matching a user-provided pattern. This is a legitimate functional requirement for a troubleshooting tool but involves direct shell command execution.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and act upon untrusted external data.
  • Ingestion points: The agent is instructed to read and analyze error messages, stack traces, and Git diffs in SKILL.md (Phase 1).
  • Boundary markers: The instructions lack explicit boundary markers or directives to ignore instructions that might be embedded within processed logs or code.
  • Capability inventory: The skill allows for local command execution (via find-polluter.sh) and file system analysis across the project.
  • Sanitization: There is no evidence of sanitization or validation of the ingested error data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 05:33 AM
Security Audit — agent-trust-hub — issue-troubleshooting