walter-writes-writer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed entirely of Markdown files (SKILL.md and references/*.md). It contains no scripts, binaries, or configuration files capable of executing system commands.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite user-provided text, which represents an indirect prompt injection surface.\n
- Ingestion points: User-supplied prose passed to the agent for stylistic rewriting (SKILL.md).\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded instructions within the input text are provided.\n
- Capability inventory: The skill does not define or use any tools, network operations, or file system modifications.\n
- Sanitization: No input filtering or validation is implemented.\n
- Assessment: While the skill processes untrusted input, the absence of dangerous capabilities (such as network access or shell execution) effectively mitigates the risk associated with this attack surface.\n- [SAFE]: No evidence of credential exposure, obfuscation, or unauthorized network activity was found during the analysis.
Audit Metadata