The Agent Skills Directory

[NO_CODE]: The skill is comprised entirely of instructional documentation (Markdown) and frontmatter configuration (YAML). No executable code, shell scripts, or binaries are included.
[SAFE]: The instructions reinforce security and reliability by requiring external validation of claims and the use of primary sources, which directly mitigates the risk of model hallucinations.
[SAFE]: The skill provides specific guidance on utilizing reputable and official sources for verification, such as UK government portals and judicial databases.
[SAFE]: The skill establishes an indirect prompt injection attack surface by requiring the use of tools to ingest external web content. \n
Ingestion points: The skill instructs the agent to use web_search and web_fetch to retrieve external data from the internet. \n
Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat fetched data as untrusted or to ignore instructions embedded within the source material. \n
Capability inventory: The skill relies on search and fetch capabilities but does not introduce scripts for file system modification, persistence, or arbitrary code execution. \n
Sanitization: No sanitization or filtering protocols are specified for the content processed through the verification workflow.

mandatory-verification