momentic-explore-prompt
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill describes an indirect prompt injection surface. The agent is instructed to gather repository facts by inspecting local files and interpolating that data into a generated prompt file (
explore-prompt.md). - Ingestion points: The agent reads local repository files, including
momentic.config.yaml, CI workflows, and application source code, to identify URLs, authentication modules, and directory structures. - Boundary markers: The generated prompt template uses sections and bullet points, though it does not explicitly use delimiters designed to neutralize malicious content embedded within the gathered facts.
- Capability inventory: The agent identifies system facts and writes them to a markdown file; it does not execute the generated configuration itself during this skill's lifecycle.
- Sanitization: No specific sanitization or validation of the gathered repository data is mentioned before it is written to the output file.
- [COMMAND_EXECUTION]: The documentation references the use of the
momenticCLI tool (e.g.,momentic ai explore diff). These are standard commands for the author's own software and do not involve arbitrary command execution or suspicious shell patterns.
Audit Metadata