proposal-drafter

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content, specifically job postings and project briefs, which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: Job postings, freelancer backgrounds, and project highlights provided during the interaction.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the job postings.
  • Capability inventory: The skill is limited to text generation and lacks risky capabilities such as file system writing, network requests, or shell command execution.
  • Sanitization: There are no explicit mechanisms for sanitizing or validating the contents of the ingested job briefs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 11:47 AM
Security Audit — agent-trust-hub — proposal-drafter