The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data to generate publishing metadata and briefs, which could be exploited to influence agent behavior through hidden instructions in assets or profiles.
Ingestion points: The skill is designed to read a brand-profile and the finished Reel asset (referenced in SKILL.md and references/scope-and-connections.md) as the primary context for its operations.
Boundary markers: There are no specific instructions or delimiters defined to isolate or instruct the agent to ignore potentially adversarial instructions embedded within the brand profile or asset metadata.
Capability inventory: The skill possesses the capability to publish content to external platforms via WoopSocial, including video files, generated captions, and cover images.
Sanitization: The instructions do not specify any validation or sanitization routines for data ingested from external assets before it is interpolated into captions or publishing briefs.

instagram-reels-publishing