ayewo-igba-ise
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script (scripts/session-evidence.py) and instructions to execute it via the shell. This utility indexes local session transcripts from ~/.codex and ~/.claude to provide structural context for analysis without context bloat.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external data including logs, transcripts, and reviewer output. It implements safety boundaries by explicitly instructing the agent to treat these files as evidence rather than actionable instructions, which prevents data-driven instruction overrides.
Audit Metadata