roadmap-communicator
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local script
scripts/changelog_generator.pyusingpython3to parse git history. While common in development skills, this represents a capability to execute code outside the immediate context of the markdown instructions. - [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection by processing external data that is not under the immediate control of the skill author.
- Ingestion points: The skill reads from
git logvia thechangelog_generator.pyscript to create narratives and stakeholder updates. - Boundary markers: No delimiters or explicit instructions are provided to the agent to ignore potentially malicious instructions embedded within commit messages.
- Capability inventory: The skill has the capability to run a Python script and generate markdown output based on the parsed data.
- Sanitization: No sanitization or validation logic is mentioned for the git log entries before they are incorporated into the agent's context.
Audit Metadata