extract-vault-protocol-logo

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection surface detected. The skill reads data from external/untrusted files and passes that data as input to another automated skill.
  • Ingestion points: Protocol-specific YAML files located in eth_defi/data/vaults/metadata.
  • Boundary markers: Absent. There are no instructions to the agent to sanitize or ignore instructions embedded within the YAML metadata or the resolved homepage links.
  • Capability inventory: File system read access, file system write access to eth_defi/data/vaults/original_logos/, and the ability to trigger the extract-project-logo skill.
  • Sanitization: None detected. The skill directly interpolates values from files into the next step's inputs.
  • [DATA_EXPOSURE] (SAFE): The skill accesses local repository data (eth_defi/data/vaults/metadata) and writes to specific subdirectories. These actions are consistent with the stated primary purpose of maintaining protocol metadata and do not target sensitive user files or credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:15 PM