team-question
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data that may contain malicious instructions.
- Ingestion points: The skill executes
gh issue view <url> --json title,bodyinSKILL.mdto fetch content from a user-provided URL. - Boundary markers: No explicit delimiters are specified when passing the issue content as the 'full description' to the downstream agent.
- Capability inventory: The skill can write files to the local file system (
docs/plans/) and execute shell scripts. - Sanitization: There is no evidence of filtering or validation of the fetched issue body before it is passed into the agent's context.
- [COMMAND_EXECUTION]: The skill executes local commands and scripts necessary for its primary workflow.
- Evidence: It runs a bundled shell script
scripts/prepare-plan-dir.shto initialize directory structures. - Evidence: It uses the
gh(GitHub CLI) tool to retrieve issue data. Both uses are well-defined and strictly related to the skill's purpose of managing development tasks.
Audit Metadata