resolving-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest external data that could contain malicious instructions designed to influence the agent's behavior during conflict resolution or test execution.\n
- Ingestion points: Step 2 in
SKILL.mdinstructs the agent to read commit messages, check PRs, and original issues/tickets.\n - Boundary markers: There are no boundary markers or specific instructions for the agent to ignore or delimit embedded commands within the retrieved data.\n
- Capability inventory: Step 4 in
SKILL.mdinstructs the agent to run automated checks, including typechecks, tests, and formatting tools, which often involve executing shell commands or project scripts.\n - Sanitization: No sanitization, validation, or filtering of the external data is specified before it is processed or before the automated checks are run.\n- [NO_CODE]: The skill is composed entirely of natural language instructions and YAML configuration metadata; it does not include any scripts, binaries, or source code.
Audit Metadata