qa
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files (e.g.,
docs/UBIQUITOUS_LANGUAGE.mdanddocs/CONTEXT_MAP.md) to guide the generation of GitHub issues. This presents a surface for indirect prompt injection if these files contain malicious instructions designed to influence the agent's behavior during the QA session. - Ingestion points:
docs/UBIQUITOUS_LANGUAGE.md,docs/CONTEXT_MAP.md(as described in SKILL.md). - Boundary markers: None specified for file content ingestion.
- Capability inventory: File system read access; network write access via the
ghtool. - Sanitization: No explicit sanitization or filtering of file content before processing.
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh issue create) to perform write operations on a remote repository. The instructions specify that issues will be filed and shared without requesting a manual review from the user first, which increases the degree of autonomy and reduces human oversight.
Audit Metadata