skills/erphq/skills/image-upload/Gen Agent Trust Hub

image-upload

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill instructs the agent to retrieve authentication data from the ~/.build-host/credentials.json file to interact with the build.host API.
  • [PROMPT_INJECTION]: The skill interacts with untrusted data from user repositories, which can lead to indirect prompt injection as it lacks explicit boundary markers or sanitization instructions for that content. * Ingestion points: The project directory and git repository specified in the Required Context (SKILL.md). * Boundary markers: Absent. * Capability inventory: File system edits and interaction with the build.host API for deployment and environment management (SKILL.md). * Sanitization: Not specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 04:43 PM
Security Audit — agent-trust-hub — image-upload