The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for transcript analysis and content creation. No malicious code, obfuscation, or unauthorized access to system resources was found.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external transcripts (Ingestion point: Transcript input required in SKILL.md). There are no explicit boundary markers or instructions to ignore embedded commands within the transcript (Boundary markers: Absent). However, the skill does not request or use any tools that could be exploited by a prompt injection, such as shell commands, file writing, or network operations (Capability inventory: None). No sanitization or filtering of the transcript content is specified (Sanitization: Absent).

clip-factory