qa
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
gh issue createcommand to submit user-reported bugs and discovered context to an external repository on GitHub. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from the local codebase to inform its actions.
- Ingestion points: The skill reads
UBIQUITOUS_LANGUAGE.mdand uses an 'Explore' subagent to read arbitrary files within the codebase for domain context. - Boundary markers: No delimiters or 'ignore instructions' warnings are used when interpolating file content into the agent's context.
- Capability inventory: The skill can execute the
ghCLI tool to write data to external GitHub repositories and can spawn subagents to further explore the file system. - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the codebase before it is used to generate the GitHub issue body.
Audit Metadata