skill-content-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists exclusively of Markdown files (
SKILL.md,EASEL-META.md,references/strategy-frameworks.md). No executable scripts (Python, JavaScript, Shell) or binary files are present, eliminating the risk of direct malicious code execution. - [DATA_EXPOSURE]: The skill reads from local profile files such as
identity.md,platforms.md, andaudience.md, as well as a shared configuration file../../shared/pillar-and-cadence.md. This is a standard pattern for personalizing agent output based on user-provided context and does not involve accessing sensitive system credentials or private keys. - [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data via user profile files.
- Ingestion points: Data is read from
identity.md,platforms.md,audience.md, andstyle.mdto customize the strategy output. - Boundary markers: The instructions do not define explicit delimiters for these profile inputs.
- Capability inventory: The agent's capabilities are restricted to generating Markdown text and saving it to
outputs/内容策略/content-strategy.md. There are no network requests, shell command executions, or dynamic code evaluation capabilities. - Sanitization: No specific sanitization or filtering of profile content is mentioned.
- Context: Given the lack of dangerous capabilities, this ingestion surface represents a low-risk design for document generation purposes.
Audit Metadata