doc-flow-diagram-generator

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection when parsing documentation from external sources.
  • Ingestion points: Raw text content is ingested from external URLs via scripts/single_page_parser.py.
  • Boundary markers: There are no explicit delimiters or system instructions to treat the analyzed content as untrusted data.
  • Capability inventory: The skill has the ability to read from the network and process textual workflows.
  • Sanitization: The parser extracts text content without filtering or sanitizing it for embedded instructions.
  • [DATA_EXFILTRATION]: The skill performs network operations to arbitrary domains.
  • Network operations: The scripts/single_page_parser.py script uses the requests library to fetch content from user-specified URLs, which could be used for Server-Side Request Forgery (SSRF) if targeted at internal infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 08:46 AM