cost-report
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the Bash tool to run a Node.js one-liner that parses a local JSON file (
docs/benchmarks/runs/latest.json) to extract summary data for the report. - [EXTERNAL_DOWNLOADS]: The documentation references the command
npx @claude-flow/cli@latest, which instructs users to download and execute a package from the npm registry. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes data from external sources to build the cost report.
- Ingestion points: Result sets from
mcp__claude-flow__memory_search(cost-tracking namespace) and data fromdocs/benchmarks/runs/latest.json. - Boundary markers: No specific delimiters or safety instructions are defined to separate ingested data from the report instructions.
- Capability inventory: Access to the
Bashshell and several memory management tools. - Sanitization: No explicit sanitization or filtering is performed on the ingested data prior to interpolation into the final report.
Audit Metadata