p-agent-doc-writing
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to read, analyze, and rewrite agent instruction files (such as SKILL.md and AGENTS.md). This creates a vulnerability surface where malicious instructions embedded in the documents being processed could influence the agent's behavior.
- Ingestion points: According to the '编写流程' (Writing Flow) in
SKILL.md, the agent is instructed to first read target files, upper-level instructions, and adjacent documentation. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts to separate the content of the analyzed files from the agent's core instructions.
- Capability inventory: The skill has the capability to substantively restructure and rewrite files on the filesystem based on the ingested content.
- Sanitization: There is no mention of sanitization, filtering, or validation logic for the external content before it is processed and used to generate new documentation.
Audit Metadata