mintlify-docs-updater
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The
scripts/ingest_markdown_doc.pyscript takes a--sourceargument that is passed directly toPath.read_text()after resolution. Since there is no validation to ensure the source path is within an expected directory, the agent could be manipulated into reading sensitive system files (like SSH keys or configuration files) and copying their content into the publicdocs/directory. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted user-supplied Markdown files.
- Ingestion points: Content is read from the path provided to the
--sourceflag inscripts/ingest_markdown_doc.py. - Boundary markers: The skill does not use delimiters or instructions to isolate the ingested text from the agent's logic.
- Capability inventory: The script can read from any accessible file path and write to the repository's
docs/folder anddocs/docs.json. - Sanitization: There is no validation or filtering performed on the body of the ingested Markdown content.
- Ingestion points: Content is read from the path provided to the
Audit Metadata