team-release
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
BashandTasktools to perform operational tasks such as cutting release branches, tagging version control, and executing deployment sequences to production environments. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes untrusted data from the repository (e.g., version files and changelog content) and uses it to drive automated workflows.
- Ingestion points: The agent reads repository content to generate checklists and changelogs in Phase 2 and Phase 6 as described in
SKILL.md. - Boundary markers: Absent. There are no instructions to wrap untrusted data in delimiters or to ignore potential instructions embedded within processed project files.
- Capability inventory: The skill has access to
Bash,Write,Edit, andTaskacross all scripts and phases inSKILL.md, allowing it to modify the file system and execute shell commands. - Sanitization: Absent. There is no mention of validating or escaping content retrieved from external files before it is processed by sub-agents or shell tools.
Audit Metadata