dbs-content-risk-check
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, credential exposure, or unauthorized command executions were found. The skill operates entirely within the agent's textual context without requesting external network access or file system operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input, such as social media captions, OCR text, and comments, which could theoretically contain malicious instructions. However, the skill does not use any sensitive tools (no network access, subprocess execution, or file writing capabilities), which mitigates the risk. Furthermore, the instructions explicitly prohibit the agent from helping users bypass filters or providing jailbreak-style 'anti-review' advice.
- [METADATA_POISONING]: The skill's metadata and description accurately reflect its intended functionality of identifying content risks for creators. No deceptive instructions were found in the YAML frontmatter or comments.
Audit Metadata