suggest
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the vendor-specific
@ericrisco/rscCLI to manage project skills, synchronize environment states, and perform diagnostic repairs.\n- [EXTERNAL_DOWNLOADS]: Fetches and installs additional skill packages from the vendor's registry when the user confirms a suggestion.\n- [DYNAMIC_EXECUTION]: Dynamically constructs shell commands using variable skill identifiers and user-provided task descriptions, such asnpx @ericrisco/rsc consult \"<task>\"andnpx @ericrisco/rsc add <id>.\n- [INDIRECT_PROMPT_INJECTION]: The skill monitors user interaction to detect gaps in installed capabilities. This represents an injection surface where user-supplied data influences tool selection and command parameters.\n - Ingestion points: User prompts and task descriptions.\n
- Boundary markers: None explicitly defined in the command interpolation templates.\n
- Capability inventory: Shell command execution via
npx.\n - Sanitization: Not explicitly implemented in the instructions; however, risks are mitigated by the requirement for manual user confirmation before any installation command is executed.
Audit Metadata