Skills
skills/orcaqubits/agentic-commerce-skills-plugins/webmcp-polyfill/Gen Agent Trust Hub

webmcp-polyfill

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation, README files, and package information from well-known services such as GitHub and NPM.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface (Category 8). It ingests untrusted data from external URLs and search results while the agent has access to sensitive tools like Bash and Write.
  • Ingestion points: External content fetched via WebSearch and WebFetch as described in SKILL.md.
  • Boundary markers: Absent; there are no instructions to the agent to disregard or isolate instructions found in the external content.
  • Capability inventory: Bash, Write, Edit, Read, Grep, Glob.
  • Sanitization: Absent; no validation or escaping of the fetched content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 06:10 AM