portable-transplant
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple documentation files which could contain instructions intended to manipulate the translation logic or the generated output.\n
- Ingestion points: epics.md, component-spec.md, prd.md, and architecture.md (as described in SKILL.md Step 1).\n
- Boundary markers: The skill instructions do not specify any delimiters or ignore-previous-instruction markers when reading and interpolating the contents of these files.\n
- Capability inventory: The skill has the capability to read any user-specified file and write new files to the _portable-transplant/ directory (as described in SKILL.md Step 6).\n
- Sanitization: There is no mention of text validation or sanitization for the content processed from external documents before it is used to generate the final output.
Audit Metadata