The Agent Skills Directory

[SAFE]: No security issues were detected in this skill. The instructions focus on social media strategy, content repurposing, and engagement frameworks. The skill uses standard local context files (e.g., .agents/product-marketing-context.md) and provides templates for user-driven content creation.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes external content like blog posts, transcripts, and podcast summaries for repurposing.
Ingestion points: The skill reads .agents/product-marketing-context.md (mentioned in SKILL.md) and is designed to ingest user-provided transcripts and blog posts (referenced in SKILL.md and evals/evals.json).
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present.
Capability inventory: The skill does not use any dangerous capabilities such as subprocess execution, file writing, or network operations.
Sanitization: No sanitization or filtering of external content is performed.
Note: Given the absence of dangerous capabilities, this surface poses no significant risk.

social-content