writing-beats
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied markdown files referred to as 'raw material' to generate its output. This creates a surface where instructions embedded within the raw material could potentially influence the agent's behavior.
- Ingestion points: Raw material markdown files provided by the user (referenced in SKILL.md).
- Boundary markers: None explicitly defined to separate user data from instructions.
- Capability inventory: File reading (raw material), file writing (article draft), and interactive user dialogue.
- Sanitization: No specific sanitization or filtering of the raw material is described.
- [SAFE]: The use of the term 'exploit' in the description refers to the 'explore/exploit' decision-making paradigm in the context of writing workflow, rather than a technical security exploit.
- [SAFE]: The skill includes configuration ('disable-model-invocation: true' and 'allow_implicit_invocation: false') that restricts its execution environment, following security best practices.
Audit Metadata