projects

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of shell commands (curl) to perform CRUD operations on an external project management API.
  • It includes logic to verify environment variables (LAYERPROOF_BASE_URL, LAYERPROOF_API_KEY) and conditionally source configuration from a .env.local file.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection via data ingested from the external API.
  • Ingestion points: Data fields such as project names, descriptions, and metadata are retrieved from the API and processed within the agent's context.
  • Boundary markers: The instructions lack specific delimiters or warnings to treat API-provided content as untrusted data.
  • Capability inventory: The agent has the capability to execute shell commands (curl) and read/source local environment files.
  • Sanitization: There is no evidence of sanitization or validation of the content received from the API before it is utilized in further agent workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 08:43 AM
Security Audit — agent-trust-hub — projects