The Agent Skills Directory

Remote Code Execution (CRITICAL): The skill documentation includes a command curl -fsSL https://cli.inference.sh | sh for installation. This is a classic RCE vector where the content of the remote script is executed without verification. This finding is confirmed by the provided automated scanner alert.
External Downloads (HIGH): The skill installs the infsh CLI and additional components using npx skills add from the inference-sh organization, which is not on the trusted external sources list.
Indirect Prompt Injection (LOW):
Ingestion points: The skill is designed to process external content such as blog posts and podcast transcripts (e.g., in the 'Podcast Episode -> Blog Post' recipe).
Boundary markers: Absent. The skill does not use delimiters or instructions to prevent the agent from following instructions hidden within the source content.
Capability inventory: The skill has access to the Bash tool and infsh which can post to social media (x/post-create) and run remote AI models.
Sanitization: Absent. Content extracted from transcripts or blogs is passed directly as input to subsequent tools.

content-repurposing