The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its primary function is to process untrusted data from external sources.
Ingestion points: The skill accepts source content in numerous formats, including LinkedIn posts, blogs, YouTube scripts, newsletters, transcripts, and links to external articles as described in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or provide the agent with explicit instructions to ignore or sanitize embedded commands within the source content.
Capability inventory: The skill utilizes lib.publish to post content to https://x.com/compose/tweet. It also accesses reference files on the local filesystem, such as voice-profile.md, hook-formulas.md, and algorithm-heuristics.md.
Sanitization: There is no evidence of sanitization, escaping, or filtering of the external content before it is interpolated into the transformation process.

x-repurposer