safe-push
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands such as
git,grep,xargs, andsleep. These are used to analyze diffs, scan tracked files, audit commit messages, and implement staggered push strategies for rate limiting. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external repository content and configuration files, which presents a potential injection surface.
- Ingestion points: Content is retrieved from
git diff,git log, and repository files viagit ls-files. It also reads patterns from a user-managed configuration file at~/.claude/safe-push-blocklist. - Boundary markers: No explicit boundary markers or 'ignore' instructions are used when processing repository content.
- Capability inventory: The agent has the ability to execute shell commands and perform
git pushoperations. - Sanitization: The skill filters comments and empty lines from the personal blocklist configuration but does not perform additional escaping of shell metacharacters before including the patterns in shell commands.
Audit Metadata