acp-extensions-authoring

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a workflow for authoring protocol extensions that involves retrieving documentation from external sources.
  • Ingestion points: The agent is instructed in SKILL.md to fetch documentation via WebSearch and WebFetch from GitHub repositories and the OpenAI developer site.
  • Boundary markers: Absent. There are no instructions to differentiate between the agent's core instructions and data found in external documents.
  • Capability inventory: The workflow involves processing the retrieved data using tools including Bash, Write, and Edit.
  • Sanitization: Absent. The skill does not describe any methods for validating or escaping external data before it is incorporated into the authoring process.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 06:10 AM
Security Audit — agent-trust-hub — acp-extensions-authoring