The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes information from external regulatory sources, which constitutes a potential attack surface for indirect prompt injection if an attacker were to control content on monitored sites.
Ingestion points: External websites defined in SKILL.md including legislation.gov.uk, EUR-Lex, and other official regulatory portals.
Boundary markers: The skill does not define specific delimiters to isolate external text from internal instructions.
Capability inventory: The skill's functionality is restricted to text summarization and reporting; it does not possess capabilities for file writing, network exfiltration of local data, or command execution.
Sanitization: There is no mention of sanitization or filtering of the fetched content within the prompt instructions.
[SAFE]: The skill contains explicit safety guidelines (NEVER characterize as legal advice) and relies on highly reputable, official government and institutional sources for data.

regulatory-monitoring