The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its documentation fetching capabilities combined with high-privilege tool access.\n
Ingestion points: The skill instructs the agent to use WebSearch and WebFetch to retrieve live documentation from external websites (SKILL.md).\n
Boundary markers: No specific delimiters or safety instructions are provided to distinguish between retrieved documentation and agent instructions.\n
Capability inventory: The skill allows access to powerful tools including Bash, Write, and Edit, which could be exploited if malicious instructions are present in the fetched content (SKILL.md).\n
Sanitization: The skill lacks mechanisms to sanitize or validate content retrieved from external sources before processing.

php-testing