ralph-specum-index
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local codebase (controllers, services, models, etc.) to generate documentation without explicit boundary markers or sanitization instructions. This creates a vulnerability surface where malicious code or comments within the project could attempt to override the indexing instructions or manipulate the final output artifacts.
- Ingestion points: Codebase files scanned during the indexing process as defined in
SKILL.md(Step 2). - Boundary markers: Absent. The instructions do not specify using delimiters or 'ignore' blocks when the agent parses file content.
- Capability inventory: The skill has file system read access for scanning the codebase and file system write access for generating artifacts in the
specs/.index/directory. - Sanitization: Absent. There are no instructions provided for escaping or validating the content extracted from source files before writing them into markdown index files.
Audit Metadata