skills/hashintel/labs/spike/Gen Agent Trust Hub

spike

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content through the $ARGUMENTS variable to define the research question and experiment approach, which the agent then executes.
  • Ingestion points: Input is accepted via the $ARGUMENTS variable in SKILL.md and used to drive the technical procedure.
  • Boundary markers: The skill lacks explicit delimiters or instructions to prevent the agent from following potential commands embedded within the provided arguments.
  • Capability inventory: The agent is instructed to create files, install dependencies, and execute code (described in SKILL.md under Step 2: Minimal experiment).
  • Sanitization: No validation or escaping of the input arguments is specified.
  • Remediation: Mitigation can be improved by wrapping input in specific delimiters and instructing the agent to treat the content strictly as data for the research question.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 01:31 AM
Security Audit — agent-trust-hub — spike