sove-blog-writer
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 and analyze user-provided materials and project files to ensure that the blog content is technically accurate and well-informed. This capability creates an attack surface for indirect prompt injection, where an attacker could place malicious instructions in those files to manipulate the agent's behavior or output.\n
- Ingestion points:
SKILL.md(Step 3: "先保证事实可靠，再组织表达") instructs the agent to check "用户材料" (user materials) and "项目文件" (project files).\n - Boundary markers: There are no explicit instructions to use delimiters or to treat the content of these files as untrusted data.\n
- Capability inventory: The skill is primarily intended for text generation and blog writing; it does not explicitly request tool access for file system writes, network requests, or system modifications in its configuration.\n
- Sanitization: No sanitization or validation of the ingested content is described in the workflow.\n- [NO_CODE]: The skill consists entirely of instructional markdown and YAML configuration. It does not contain any executable scripts (Python, JavaScript, shell) or binary files, which significantly reduces the risk of direct remote code execution or privilege escalation.
Audit Metadata