retro

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze session logs which are a source of untrusted external data.
  • Ingestion points: SKILL.md (Step 2) directs the agent to search through session logs on the machine.
  • Boundary markers: Absent; there are no instructions to use delimiters or to ignore instructions found within the logs.
  • Capability inventory: The agent has read access to repo configuration files (CLAUDE.md, AGENTS.md, CODING_STANDARDS.md) and generates suggestions for environmental changes.
  • Sanitization: Absent; no validation or filtering is mentioned for the log content being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 01:31 AM
Security Audit — agent-trust-hub — retro