skills/bsene/skills/dantotsu/Gen Agent Trust Hub

dantotsu

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from potentially untrusted external sources, which creates a theoretical attack surface for indirect prompt injection.
  • Ingestion points: Step 3 of the workflow in SKILL.md instructs the agent to check external issue trackers and history for recurring defect patterns.
  • Boundary markers: The skill uses a structured Markdown template (_template.md) for its final output, which provides implicit delimiters, though it does not explicitly instruct the agent to ignore instructions embedded in the source tickets.
  • Capability inventory: The skill's primary functions are text analysis and report generation (writing to .md files). It does not involve high-risk capabilities such as command execution, network requests to untrusted domains, or privileged system access.
  • Sanitization: The instructions do not define specific sanitization or filtering logic for the content retrieved from issue trackers before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 11:18 PM
Security Audit — agent-trust-hub — dantotsu