The Agent Skills Directory

[PROMPT_INJECTION]: No patterns of prompt injection, role-play overrides, or system prompt extraction instructions were detected. The instructions remain within the scope of content strategy expertise.
[DATA_EXFILTRATION]: The skill instructs the agent to read local project files (e.g., .agents/SYSTEM/ARCHITECTURE.md) to understand the environment, which is standard behavior for project-aware agents. No network exfiltration commands (curl, wget) or hardcoded external destinations were found.
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or sensitive credentials were found in the skill or plugin metadata.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts. No package installation commands (npm, pip) are present.
[COMMAND_EXECUTION]: No dangerous shell commands, privilege escalation (sudo), or persistence mechanisms were detected.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data such as analytics and bookmarked research. While this presents a surface area for indirect prompt injection, the risk is minimal as the skill's capabilities are focused on text synthesis and organization rather than executing code or performing sensitive operations.

strategy-expert