The Agent Skills Directory

[SAFE]: The skill serves as a template-based generator for social media marketing. All instructions and templates align with the stated goal of providing TikTok strategies.
[SAFE]: No prompt injection or behavior override patterns were detected. The rules provided are stylistic constraints (e.g., forbidding traditional introductions to improve retention) rather than safety filter bypasses.
[SAFE]: No sensitive data exposure or exfiltration patterns were identified. The skill does not access local configuration files, environment variables, or credentials.
[SAFE]: No obfuscation techniques, such as hidden Base64 strings or homoglyph attacks, were found in the instructions or example files.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided niches and topics to generate scripts. While it lacks boundary markers for this data, there are no exploitable capabilities (such as network access, file writing, or command execution) that would make this surface dangerous.
Ingestion points: User-provided inputs for "Niche / topic", "Target FYP", and "Format type" defined in SKILL.md.
Boundary markers: Absent; user input is interpolated directly into the response text.
Capability inventory: None; the skill only generates markdown text and does not invoke any external tools or scripts.
Sanitization: Absent; the skill relies on the underlying model's inherent safety guardrails.

tiktoker-pro