dhdna-profiler
Pass
Audited by Gen Agent Trust Hub on May 28, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed solely of markdown instructions and reference materials. It contains no executable scripts, binaries, or code in any language, precluding categories such as remote code execution or unauthorized command execution.
- [SAFE]: There are no hardcoded secrets, API keys, or credentials present in the skill files.
- [PROMPT_INJECTION]: The skill's primary function involves analyzing untrusted text provided by users or read from the environment. This represents a surface for indirect prompt injection.
- Ingestion points: The agent is instructed to analyze any provided text or conversation history (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore commands within the analyzed text are defined.
- Capability inventory: The skill utilizes 'Read' and 'Write' tools for its analysis workflow.
- Sanitization: No input sanitization or validation logic is present to handle malicious instructions embedded in the analyzed text.
Audit Metadata