The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from both local files and remote URLs provided by the user, which could contain hidden instructions designed to influence the agent's behavior during documentation or subsequent implementation planning.
Ingestion points: Reads content from local file paths and remote URLs as described in Step 3.1 and 3.3.
Boundary markers: The skill does not specify the use of delimiters or 'ignore' instructions when processing or displaying the external code content.
Capability inventory: The skill possesses network read capabilities (fetching URLs), local file read capabilities, and local file write capabilities (creating YAML and Markdown artifacts).
Sanitization: There is no mention of sanitizing or validating the ingested content before it is displayed or written to files.
[EXTERNAL_DOWNLOADS]: The skill fetches content from external URLs provided by the user in Step 3.3 to serve as reference code patterns. While user-directed, this involves downloading content from arbitrary remote sources.
[COMMAND_EXECUTION]: The skill executes shell commands to establish its output environment, specifically using mkdir -p to create the artifacts directory structure as described in Step 4.1.

style-anchors-collection