workflow-merge-conflicts

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies and processes information from external, potentially untrusted sources to determine the intent behind code changes.
  • Ingestion points: In SKILL.md, the agent is instructed in step 2 to "read the commit messages, check the PRs, check the original issues or tickets."
  • Boundary markers: The instructions do not specify the use of boundary markers or delimiters to separate the external data from the agent's instructions, nor do they include warnings to ignore instructions embedded within those external sources.
  • Capability inventory: The skill utilizes shell command execution (via git and project-specific commands like pnpm test) and file system write access to resolve conflicts in the working directory.
  • Sanitization: There is no mention of sanitizing, escaping, or filtering the content retrieved from commits or PRs before the agent interprets it.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 11:27 PM