issue-search
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill dynamically constructs shell commands using the
ghCLI based on user-provided keywords and error messages. If malicious input is provided as a question (e.g., command chaining characters), it could lead to arbitrary command execution within the environment context. - [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8).
- Ingestion points: Technical terms and error messages extracted from user questions, and issue data retrieved from GitHub search results in
SKILL.md. - Boundary markers: None. The skill does not use delimiters or instructions to ignore embedded commands in the fetched GitHub issue content.
- Capability inventory: Executes shell commands via
ghCLI and performs network operations viaWebFetchas described inSKILL.md. - Sanitization: None. User-derived keywords are passed directly to
gh issue list --searchandWebFetch(url, prompt=...).
Audit Metadata