steedos-files

Fail

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: HIGHCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The documentation in SKILL.md contains literal strings for AWS S3 credentials (AKIAIOSFODNN7EXAMPLE and wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY) within the S3 Configuration section. While these are common documentation examples, they match the structure of sensitive access keys.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data through file uploads, creating a potential vector for indirect prompt injection.
  • Ingestion points: Files uploaded to the /api/v6/files/:collectionName endpoint described in SKILL.md.
  • Boundary markers: Absent; there are no instructions provided to the agent to treat uploaded content as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill enables uploading, downloading, and metadata management for files, providing a path for external data to enter the agent context.
  • Sanitization: No mechanisms for validating, sanitizing, or filtering the content of uploaded files are mentioned.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Apr 25, 2026, 10:36 AM
Security Audit — agent-trust-hub — steedos-files