The Agent Skills Directory

[SAFE]: The skill demonstrates best practices by incorporating ethical guidelines, specifically instructing the agent to refuse requests to guarantee virality, fabricate performance metrics, or bypass mandatory branded content disclosures.
[SAFE]: No hardcoded credentials or sensitive local file paths were detected. References to API endpoints (e.g., /social-accounts/{id}/platform-inputs) in documentation utilize placeholders and are intended for standard interaction with the WoopSocial toolset.
[PROMPT_INJECTION]: The skill ingests untrusted data from external profile and goal files, which could contain instructions intended to influence agent behavior.
Ingestion points: Reads brand-profile and goals-and-kpis files (identified in SKILL.md) to define tone and objectives.
Boundary markers: None; there are no instructions to use delimiters or ignore commands within the ingested text.
Capability inventory: The agent uses the WoopSocial tool to perform network operations, such as publishing and validating content.
Sanitization: No explicit sanitization or validation of the input file content is defined.

tiktok-photo-mode