boring-essay
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, persistence mechanisms, or unauthorized privilege escalation attempts were detected.
- [DATA_EXFILTRATION]: The skill reads from user-provided files in the
world-code/directory. These files contain user-defined preferences and worldview information. There is no evidence of these files being exfiltrated or transmitted over the network. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it incorporates the contents of local files into its writing process. 1. Ingestion points:
world-code/voice.md,world-code/climax.md,world-code/conversation.md,world-code/crown.md,world-code/method.md, andworld-code/creation.md. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used. 3. Capability inventory: The skill writes output files to thecontent/essays/directory as specified inSKILL.md. 4. Sanitization: No content filtering or sanitization of the input files is performed. This behavior is consistent with the skill's primary purpose of cross-domain, opinionated prose generation and is considered low-risk.
Audit Metadata