anti-slop-writing
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process and improve user-provided text drafts, which constitutes an ingestion point for potentially untrusted data. An attacker could embed malicious instructions within a draft to influence the agent's behavior during the editing process.
- Ingestion points: The agent is instructed to read drafts provided by the user in SKILL.md under the 'Edit', 'Point edit', and 'Detect' workflows.
- Boundary markers: There are no explicit delimiters (such as XML tags or special markers) defined to isolate the user's draft from the skill's instructions.
- Capability inventory: The skill's operations are limited to text analysis and rewriting; the instructions do not require the use of high-risk tools like file system writes, shell command execution, or network requests.
- Sanitization: No input sanitization or escaping mechanisms are specified for the drafts being processed.
- [EXTERNAL_DOWNLOADS]: The skill references and instructs the agent to read supplementary documentation and style guides from external GitHub repositories belonging to the author and well-known technology organizations. These resources provide additional context and rules for the editing tasks and are handled as trusted documentation sources.
Audit Metadata