The Agent Skills Directory

[PROMPT_INJECTION]: The skill's instructions focus on social media strategy and content creation. There are no attempts to bypass safety filters, override system instructions, or extract system prompts.
[DATA_EXFILTRATION]: No patterns for sensitive data access or external transmission were detected. The skill does not access credentials or sensitive environment variables.
[REMOTE_CODE_EXECUTION]: The skill does not include any executable scripts, shell commands, or mechanisms to download and run remote payloads. References to third-party tools (e.g., Apify, Descript, CapCut) are provided as informational resources for the user and are not invoked by the agent.
[INDIRECT_PROMPT_INJECTION]: The skill establishes an ingestion surface by instructing the agent to read marketing context files (e.g., .agents/product-marketing.md) and process user-provided content for repurposing.
Ingestion points: Reads local context files and processes user-provided long-form content.
Boundary markers: The instructions do not define specific delimiters for separating context data from instructions.
Capability inventory: The skill has no file-write, network, or subprocess capabilities.
Sanitization: No active sanitization is performed, but the lack of capabilities prevents exploitation.
[COMMAND_EXECUTION]: No shell commands or system-level interactions are present in the documentation or metadata.

social