The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves auditing external websites, which introduces a data ingestion surface for untrusted content.
Ingestion points: The agent is instructed to audit site content fetched via tools like web_fetch and curl (referenced in SKILL.md).
Boundary markers: There are no explicit instructions or delimiters defined to separate the fetched website content from the agent's instructions, nor are there warnings to ignore potentially malicious instructions embedded in the external data.
Capability inventory: The skill focuses on information analysis and reporting; it does not request high-privilege capabilities such as file system modification, credential access, or arbitrary command execution on the host system.
Sanitization: While the skill notes that web_fetch strips <script> tags, there is no logic provided to sanitize other HTML elements or metadata that could contain adversarial prompts.

seo-audit