The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents an Indirect Prompt Injection surface because it is designed to ingest and analyze full-page content from arbitrary external websites (blogs, tech reports, product pages). Maliciously crafted content on these pages could contain instructions intended to override the agent's behavior during the analysis phase.
Ingestion points: Untrusted web content fetched via the apify rag-web-browser tool as specified in SKILL.md.
Boundary markers: Absent; the skill instructions do not define specific delimiters or "ignore" commands to separate ingested data from system instructions.
Capability inventory: The manifest focuses on reading and analysis; no high-risk capabilities like arbitrary command execution, file-system writes, or direct network exfiltration are defined in this specific skill.
Sanitization: Absent; there is no evidence of content filtering or sanitization performed on the ingested data before processing.

web-research