writing-clearly
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, including user-provided text, emails, and documentation, which may contain malicious instructions.
- Ingestion points: Text provided for rewriting, distilling, or tone-matching in SKILL.md and references/messages-and-emails.md.
- Boundary markers: Absent. There are no explicit instructions to treat the input text as data and ignore any embedded commands.
- Capability inventory: The skill instructs the agent to update local configuration files (CLAUDE.md or AGENTS.md) and persistent memory based on the processed text within its feedback loop (SKILL.md).
- Sanitization: Absent. The skill lacks instructions to sanitize or validate external content before it is used to modify the environment's configuration.
- [NO_CODE]: This skill consists entirely of markdown instructions and documentation without any executable scripts or binary files.
Audit Metadata