bfs-synthesize-documents
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's logic is entirely dedicated to document synthesis, consensus building, and disagreement mapping. No malicious patterns such as credential harvesting, unauthorized data exfiltration, or obfuscation were detected.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it is designed to ingest and process untrusted data from external sources. Malicious instructions embedded in source documents could potentially influence the agent's output or actions.
- Ingestion points: The workflow retrieves content from user-provided file paths, attachments, URLs, and prior chat history as defined in Step 1 of
SKILL.md. - Boundary markers: The instructions do not specify the use of clear delimiters or "ignore embedded instructions" headers to isolate untrusted source content.
- Capability inventory: The skill utilizes external web searches for factual verification (Step 6) and creates new Markdown files on the filesystem (Step 8).
- Sanitization: There is no explicit logic provided for sanitizing or validating the content extracted from input documents.
Audit Metadata