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), andglab(GitLab CLI) to perform repository investigations, check authentication status, and create issues in bug trackers. - [EXTERNAL_DOWNLOADS]: The skill uses
WebSearchandWebFetchtools 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/WebFetchand 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