audit-performance

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which creates a potential surface for indirect prompt injection. Ingestion points: External web content fetched via firecrawl:firecrawl_search and firecrawl:firecrawl_scrape, and production logs via sentry:search_events and sentry:search_issues. Boundary markers: Absent; instructions do not specify the use of delimiters or warnings to ignore embedded instructions in external data. Capability inventory: The skill allows for local shell execution (npm, npx, curl), file modification, and database query execution (EXPLAIN ANALYZE). Sanitization: Absent; the agent is expected to use the retrieved data to inform its reasoning and direct code fixes.
  • [COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands for auditing, such as npm run build, npx @lhci/cli autorun, and curl for checking network headers. These commands provide the agent with active execution capabilities in the local environment.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to fetch and execute packages from the npm registry, such as @lhci/cli and source-map-explorer.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 11:26 PM