create-md-from-browsermcp-snapshot
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external webpage data which is an untrusted source.
- Ingestion points: The
scripts/parse_snapshot.pyscript reads accessibility tree snapshots from a file specified via the--inputargument. - Boundary markers: The script does not wrap the converted content in explicit boundary markers or warnings to notify downstream agent processes that the content is untrusted.
- Capability inventory: The skill has the capability to write files to the local system via the
--outputargument in thescripts/parse_snapshot.pyscript. - Sanitization: The script parses the structural elements of the accessibility tree but does not sanitize the text content for potential natural language instructions that could trigger unintended agent behavior.
Audit Metadata