github-issue-search
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
prbotCLI tool via the Bash environment to perform searches on GitHub repositories. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data from GitHub issues and pull requests.
- Ingestion points: Data fetched from the GitHub API (including titles, labels, and author info) as defined in SKILL.md.
- Boundary markers: None. The skill does not implement delimiters or instructions to ignore potential commands within the retrieved data.
- Capability inventory: The skill has access to the
Bashtool to execute commands. - Sanitization: There is no evidence of sanitization or escaping of the external content before it is provided to the agent.
- [DATA_EXFILTRATION]: The skill accesses the sensitive local file
.env.localto load credentials such asGH_TOKENorGH_TOKEN_COMFY_PR. This access is part of the intended authentication flow for the Comfy-Org infrastructure.
Audit Metadata