qodo-merge
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze data from external and potentially untrusted sources, including pull request diffs, descriptions, branch names, and tickets from GitHub, GitLab, and Jira. This content is then used to generate descriptions, code suggestions, and labels.
- Ingestion points: Pull request content (diffs and descriptions), issue comments, and ticket metadata (title, description) from Jira and GitHub/GitLab issues.
- Boundary markers: The instructions do not define the use of specific delimiters or warnings to ignore instructions embedded within the ingested data.
- Capability inventory: The agent has the capability to post PR comments, apply labels, and update repository files such as CHANGELOG.md via the
/update_changelogtool. - Sanitization: There is no evidence of explicit sanitization or filtering logic applied to external content before it is processed by the AI models.
Audit Metadata