specstory-link-trail
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill parses and processes untrusted data from web fetch results stored in SpecStory history files.
- Ingestion points: Reads markdown files from the
.specstory/history/directory which contain content from external websites. - Boundary markers: Extracted data is structured into markdown tables in the final report to separate entries.
- Capability inventory: The skill uses
BashandReadtools to execute local Python scripts (parse_webfetch.py,generate_report.py) for processing. - Sanitization: The
generate_report.pyscript explicitly escapes markdown pipe characters in summaries to maintain report structure integrity.
Audit Metadata