The Agent Skills Directory

[NO_CODE]: This skill consists entirely of markdown documentation and role-playing instructions. It does not include any scripts, binaries, or configuration files that execute code directly.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on external data sources.
Ingestion points: The skill is configured to use WebSearch and WebFetch tools to ingest data from the open web (as defined in the metadata).
Boundary markers: None. There are no instructions or delimiters provided to help the agent distinguish between its own system instructions and potentially malicious instructions embedded in fetched web content.
Capability inventory: The agent has Write and Edit permissions, which could be exploited to persist malicious instructions or data into local files if the agent is manipulated by external content.
Sanitization: There are no instructions for validating, filtering, or sanitizing the content retrieved from external sources before processing it.

product-trend-researcher