The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized network operations were detected in the skill instructions.
[DATA_EXPOSURE]: The skill references local file paths for its internal knowledge base and prompt libraries (e.g., ~/work/laniameda/laniameda-hq/content-kb/ and docs/seedance/imagine-art-seedance-prompt-library.json). These paths appear to be part of the skill's legitimate operational environment for retrieving context and examples.
[PROMPT_INJECTION]: The skill includes a 'Safe Reframing' section that explicitly instructs the agent not to bypass filters or moderation systems. It provides safe cinematic alternatives for potentially sensitive terms (e.g., replacing 'fight' with 'impact sequence'), which demonstrates a defensive security posture rather than an offensive bypass attempt.

seedance-prompting