skills/arsenyinfo/skills/investigate/Gen Agent Trust Hub

investigate

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data (logs, Sentry reports, GitHub issues, and test failures), which serves as a surface for indirect prompt injection (Category 8). Ingestion points: $ARGUMENTS and external signals like logs or traces; Boundary markers: The instructions lack explicit delimiters to isolate external data from the prompt; Capability inventory: The skill is intended to be used with Sentry CLI, git, and SQL tools; Sanitization: No specific sanitization or filtering of external content is defined.
  • [SAFE]: The skill contains explicit safety rules that prohibit the transfer of secrets, tokens, or private user data and prevents the execution of destructive commands without user approval.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 09:34 PM
Security Audit — agent-trust-hub — investigate