The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external websites (skyscanner.net). This is a standard attack surface where malicious instructions could potentially be embedded in external content to influence agent behavior.
Ingestion points: Data retrieved via skyscanner_net__post_radar_web_unified_search, unbrowse_scrape, and unbrowse_run tools as described in SKILL.md.
Boundary markers: No specific delimiters or instructions are provided to the agent to treat external content as untrusted data.
Capability inventory: The skill includes tools for searching, scraping, and browser automation (unbrowse_browse_open, unbrowse_browse_act) on the target domain.
Sanitization: No explicit sanitization or validation of the fetched web content is performed within the skill instructions.
[DATA_EXPOSURE]: The skill documentation mentions the use of an API key ($UNBROWSE_API_KEY) for REST API access. It correctly identifies this as sensitive and explicitly instructs the user to store it in a secret manager and avoid committing it to configuration files.

skyscanner