issue-intelligence-analyst
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing shell commands via
gh(GitHub CLI) andgitto interact with repositories and fetch issue data. - The instructions specifically command the agent to avoid shell pipes, command chaining (&&, ||), and the generation of inline scripts (Python/Node/Ruby) to minimize the risk of command injection and unauthorized execution.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from GitHub issues, which are external and potentially attacker-controlled.
- Ingestion points: External data enters the agent context via the output of
gh issue listandgh issue viewin SKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore" instructions to prevent the model from obeying malicious commands embedded within issue titles or bodies.
- Capability inventory: The agent has the ability to execute repository management and information tools (
gh,git,which). - Sanitization: There is no evidence of sanitization, escaping, or filtering of the fetched issue content before it is clustered and synthesized by the LLM.
Audit Metadata