finish-release
Warn
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to interpolate user-provided
$ARGUMENTSdirectly into shell commands in Phase 4 (git flow release finish $VERSION) and Phase 5 (gh release create "v$VERSION"). This pattern is vulnerable to command injection if a user provides input containing shell metacharacters (e.g.,;,&&, or|) intended to execute arbitrary code. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by reading and processing external data from the git commit history and
CHANGELOG.mdand interpolating that content into thegh release createcommand notes. - Ingestion points: Git commit logs (Phase 3) and
CHANGELOG.md(Phase 5). - Boundary markers: Absent; there are no instructions to the agent to treat the content as data only or to ignore embedded instructions.
- Capability inventory: The skill has access to
Bash(git:*),Bash(gh:*), andWritetools across its execution phases. - Sanitization: No sanitization or escaping of the ingested commit messages or changelog content is performed before interpolation.
Audit Metadata