competitive-intel-writer

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes untrusted competitor data.
  • Ingestion points: Processes user-uploaded documents (PDF, Word, Excel, CRM exports) located in the input/ directory.
  • Boundary markers: No explicit delimiters or instructions are used to separate untrusted file content from the agent's instructions.
  • Capability inventory: The skill uses curl to interact with an internal bridge API (http://opencode-bridge:8000) for file handling and task execution.
  • Sanitization: Input from external documents is not sanitized or validated before being passed to the processing engine.
  • [COMMAND_EXECUTION]: The skill uses curl to communicate with a local bridge service at http://opencode-bridge:8000. This is functional behavior for document uploads and submitting analysis tasks. Secrets are managed correctly via the $OPENCODE_BRIDGE_TOKEN environment variable.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 02:21 PM
Security Audit — agent-trust-hub — competitive-intel-writer