harvest-competitive

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it is instructed to ingest untrusted data from external URLs and process it with high-privilege tools.
  • Ingestion points: The skill uses the WebFetch tool to retrieve content from arbitrary, potentially attacker-controlled competitor websites.
  • Boundary markers: There are no explicit instructions or delimiters defined to isolate the fetched external content from the agent's core instructions.
  • Capability inventory: The skill is granted access to powerful tools including Bash (shell command execution), Write (file system modification), and WebFetch (network access), which could be leveraged if an attacker successfully injects instructions through a website.
  • Sanitization: The instructions do not specify any validation, sanitization, or filtering of the content retrieved from external sources before it is processed or used in subsequent steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 07:46 AM
Security Audit — agent-trust-hub — harvest-competitive