merge-strategy
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a configuration for Git commit message templates that incorporates untrusted data from external sources.\n
- Ingestion points: The
MergeTemplateDatastructure andrenderMergeMessagefunction ingest potentially attacker-controlled data such as.PRTitleand.Branchnames from the workspace environment (SKILL.md).\n - Boundary markers: The proposed implementation lacks explicit delimiters or instructions to the agent to ignore embedded instructions within these fields.\n
- Capability inventory: The skill documentation details the execution of
git mergeandgit commitcommands which use the rendered templates as command-line arguments (SKILL.md).\n - Sanitization: No sanitization or validation logic is described for the content of PR titles or branch names before interpolation into the templates.
Audit Metadata