agent-releaser
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data such as git commits and changelog entries, which presents an attack surface for indirect prompt injection.
- Ingestion points: Git commits, release notes, and the VERSION_LOG.md file.
- Boundary markers: Absent; no delimiters or protective instructions are defined to separate untrusted content from system instructions.
- Capability inventory: The skill utilizes tools like Bash, Read, Write, and Edit.
- Sanitization: No sanitization logic for external data is present in the skill definition.
- [COMMAND_EXECUTION]: The skill references the use of Bash for executing release-related tasks. While the intended use is for versioning and deployment, the execution of shell commands based on potentially untrusted input (like commit messages) should be monitored.
Audit Metadata