situation-framing
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on providing reasoning and planning for the use of the
eecommand-line utility without directly performing sensitive operations itself. - [SAFE]: Explicit instructions are provided to the agent to avoid scraping internal database paths (e.g., FrankenSQLite, CASS stores) and to strictly use the tool's JSON output for evidence gathering.
- [SAFE]: The skill includes comprehensive 'Stop/Go Gates' that require the agent to stop if data redaction fails, if raw secrets are detected, or if prompt-injection-like patterns are found in the evidence.
- [SAFE]: The included Python validation script (
scripts/validate_situation_framing_skill.py) performs integrity checks on the skill's structure, fixtures, and safety phrases. It uses standard library modules and only performs local file read/write operations for logging purposes. - [SAFE]: No network requests, credential exfiltration, obfuscation, or persistence mechanisms were detected in the skill instructions or supporting scripts.
Audit Metadata