arc-bug-finder

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes several CLI tools including git, gh (GitHub CLI), and glab (GitLab CLI) to perform repository investigations, check authentication status, and create issues in bug trackers.
  • [EXTERNAL_DOWNLOADS]: The skill uses WebSearch and WebFetch tools to conduct exhaustive online research, reaching out to authoritative documentation sites and upstream trackers to investigate reported defects.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted content from the web and OCR data from user-provided screenshots.
  • Ingestion points: Web page content retrieved via WebSearch/WebFetch and extracted text from screenshots.
  • Boundary markers: None explicitly defined in the prompts to delimit untrusted external content from agent instructions.
  • Capability inventory: The skill has the ability to execute shell commands and file persistent issues in GitHub, GitLab, and Linear trackers.
  • Sanitization: No specific sanitization or validation logic is described for the data retrieved from external sources before it is used to generate the final bug report.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 05:30 PM
Security Audit — agent-trust-hub — arc-bug-finder