memento-summary
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from coding session transcripts and external files to generate its output.
- Ingestion points: AI coding session transcripts and tmp/vault-refs.jsonl.
- Boundary markers: Absent.
- Capability inventory: Reading git logs and reading local files (tmp/vault-refs.jsonl).
- Sanitization: Instructions to exclude sensitive information such as API keys, credentials, and PII.
- [NO_CODE]: The skill contains only markdown instructions and does not include any executable scripts or binary files.
Audit Metadata