roadmap-refresh
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines a command to execute a Python script at a specific local path (
~/.claude/rag-index/specs.py). This command relies on an external toolkit being present in the user's environment. - [PROMPT_INJECTION]: The skill instructions do not contain attempts to override agent behavior or bypass safety guardrails.
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes data from user-controlled files.
- Ingestion points: Reads content from all markdown files in
docs/specs/. - Boundary markers: No boundary markers are used to isolate untrusted content from the spec files.
- Capability inventory: The skill primarily performs file read/write operations and command execution via a Python script.
- Sanitization: There is no indication of content sanitization or validation of the frontmatter being parsed from the spec files.
Audit Metadata