resolve-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of Git conflict markers, commit logs, and pull request information which could contain malicious instructions.\n
- Ingestion points: File contents with conflict markers and Git commit/PR metadata processed during the workflow in SKILL.md.\n
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the processed data.\n
- Capability inventory: The agent has the ability to execute shell commands, modify files, and interact with the local repository and GitHub CLI.\n
- Sanitization: No explicit sanitization or filtering of commit messages or conflict hunk content is performed before processing.\n- [COMMAND_EXECUTION]: In the workflow's check phase, the skill is instructed to discover and execute existing repository scripts such as those in a Makefile, justfile, or package.json. This allows the execution of arbitrary commands defined within the local repository environment.\n- [EXTERNAL_DOWNLOADS]: The skill fetches a secondary instruction file (SKILL.md for auto-commit) from the author's repository at
raw.githubusercontent.com/spacemansh/spaceman-skillsif it is not found in the local environment. This is a reference to a vendor-owned resource used for extending skill capabilities.
Audit Metadata