The Agent Skills Directory

[DATA_EXPOSURE_AND_EXFILTRATION]: The skill describes interactions with a remote API host (twitter.fetcher.sh), which is the official domain for the skill's author (fetcher-sh). The operations involve retrieving public social media data via authenticated HTTP GET requests. No sensitive local file access or unauthorized data exfiltration was identified.
[INDIRECT_PROMPT_INJECTION]: The skill defines a potential attack surface by ingesting external data from X (Twitter) profiles and searches. However, this is the intended purpose of the scraper, and the risk is assessed as safe given the nature of the tool. 1. Ingestion points: Search queries, account handles, and list IDs (SKILL.md, references/endpoints.md). 2. Boundary markers: None provided in the documentation examples. 3. Capability inventory: Outbound network requests via curl or other HTTP clients. 4. Sanitization: Not specified; the documentation assumes the agent handles parameter construction.

x-scraper