content-optimizer

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its automated processing of untrusted external content.
  • Ingestion points: The skill ingests data from external URLs provided by the user using the 'Read' tool as specified in the workflow (SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent ignores or isolates instructions embedded within the fetched content.
  • Capability inventory: The skill is configured with both 'Read' and 'Write' tool access, which creates a risk where malicious directives in a webpage could cause the agent to perform unintended file modifications (SKILL.md).
  • Sanitization: The skill does not implement any validation or sanitization of the fetched content before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 12:13 AM
Security Audit — agent-trust-hub — content-optimizer