debug-error
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates debugging through the execution of several shell commands, including git operations (git log, git bisect, git diff), text searching (ripgrep), and language-specific test runners such as npm test, pytest, cargo test, and go test.
- [EXTERNAL_DOWNLOADS]: The workflow integrates data from external services, fetching error context from Sentry's platform and performing web searches/scraping via Firecrawl to research potential fixes and library documentation.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the ingestion and processing of untrusted data from the web. This vulnerability is characterized by:
- Ingestion points: Untrusted data enters the agent context through the firecrawl_search, firecrawl_scrape, and search_issues tools in SKILL.md.
- Boundary markers: The skill lacks explicit boundary markers or instructions to ignore embedded commands within the fetched content.
- Capability inventory: The skill provides the agent with capabilities to modify source code (Phase 5) and execute arbitrary shell commands for testing (Phase 6), which could be abused if malicious instructions are ingested.
- Sanitization: There is no evidence of sanitization or validation of the external content before it influences the agent's actions.
Audit Metadata