diag-migrate
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external diagnosis notes which could contain instructions designed to manipulate the agent during the rewrite process.
- Ingestion points: Reads content from external markdown files to be migrated into the ~/ops vault.
- Boundary markers: The skill does not define specific delimiters or instructional barriers to prevent the agent from obeying commands embedded in the processed notes.
- Capability inventory: The skill has the capability to write files to ~/ops/, copy assets to ~/ops/assets/, and trigger git commits via external skill references.
- Sanitization: No sanitization or escaping mechanisms are described; instructions explicitly mandate copying parts of the source trail verbatim, including fenced outputs.
Audit Metadata