opencontext

Warn

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to install the @aicontextlab/cli package via npm. This package is not from a trusted organization or the skill author's verified namespace, which introduces risks associated with executing untrusted code and potential supply chain vulnerabilities.
  • [PROMPT_INJECTION]: The skill workflow is susceptible to indirect prompt injection because it is designed to ingest and process documentation, decision logs, and other repository artifacts that could contain malicious instructions.
  • Ingestion points: The agent loads content from arbitrary project files using the oc CLI and standard tools like Read and Grep.
  • Boundary markers: There are no instructions or delimiters provided to help the agent distinguish between trusted instructions and potentially adversarial content within the project files.
  • Capability inventory: The agent has access to sensitive capabilities including Bash and Write, which could be leveraged to perform harmful actions if the agent follows instructions embedded in the project files.
  • Sanitization: The skill does not implement any validation or sanitization for the data retrieved from repository files.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 28, 2026, 01:51 PM
Security Audit — agent-trust-hub — opencontext