diagnosing-bugs
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process various external and potentially untrusted data sources that could be used to deliver malicious instructions to the agent.
- Ingestion points: As described in
SKILL.md, the agent reads project-level documentation (GLOSSARY.md, ADRs) and diagnostic artifacts including HAR files, log dumps, core dumps, and browser-captured DOM/network data. - Boundary markers: The skill does not define specific delimiters or instructions to treat these external inputs as untrusted data, increasing the risk of the agent obeying embedded instructions.
- Capability inventory: The skill possesses significant capabilities, including general shell command execution, network requests via
curl,gitoperations, and browser automation using Playwright or Puppeteer. - Sanitization: While the skill provides high-quality guidance for redacting credentials and auth headers from captured artifacts (Phase 1), it lacks specific sanitization or filtering to prevent instruction injection from those same sources.
Audit Metadata