The Agent Skills Directory

[PROMPT_INJECTION]: The skill defines a workflow for ingesting untrusted data from public Threads posts and user profiles, which creates an indirect prompt injection surface.
Ingestion points: Public post text, user biographies, and search results from threads/search/... and threads/users/... operations in SKILL.md.
Boundary markers: None defined; the instructions do not specify delimiters to isolate external content from agent instructions.
Capability inventory: The skill is documented as read-only and does not define any executable scripts, file system writes, or command execution tools.
Sanitization: No sanitization or filtering logic is specified for the retrieved content.
[NO_CODE]: The skill contains only documentation, metadata, and instructional content. There are no executable scripts (e.g., Python, JavaScript) or binary files included in the skill package.
[SAFE]: The skill uses established OAuth patterns for authentication through the unifapi skill and references official vendor domains (unifapi.com). No evidence of credential harvesting, persistence, or malicious network operations was found.

threads