content-strategy
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and does not contain any executable scripts, binaries, or system-level configuration files. It defines a persona and workflows for content strategy development using standard natural language.
- [PROMPT_INJECTION]: There are no instructions that attempt to override safety guidelines, bypass constraints, or extract system prompts. The use of 'IMPORTANT' or 'CRITICAL' in a security context is absent; these terms are used only for workflow emphasis.
- [DATA_EXFILTRATION]: The skill does not attempt to access sensitive files like SSH keys, AWS credentials, or environment variables. It references a local marketing context file ('.claude/product-marketing-context.md') which is a standard practice for providing domain-specific knowledge to the agent.
- [REMOTE_CODE_EXECUTION]: No commands related to downloading or executing external code, installing packages, or dynamic code generation were found. The mention of web search queries is a standard capability for research-oriented agents.
Audit Metadata