xy-question-spec
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill relies on an external API at
https://api.xyskill.xyz/v1/atoms/searchto retrieve knowledge data. This is a vendor-owned resource used for the skill's primary function. - [COMMAND_EXECUTION]: The
SKILL.mdfile contains instructions for the agent to execute a bundled Python script,scripts/atoms-search.py, to query the atom database. This script is used locally to manage data retrieval efficiently and prevent excessive resource consumption. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a remote API and a local file (
references/atoms.jsonl) to construct its responses, creating a vulnerability surface where untrusted data could influence agent behavior. - Ingestion points:
references/atoms.jsonl(local) andhttps://api.xyskill.xyz/v1/atoms/search(remote). - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore commands potentially embedded in the retrieved data.
- Capability inventory: The skill has capabilities for local file reading, network POST requests, and shell execution of its own utility scripts.
- Sanitization: There is no evidence of explicit sanitization or validation of the content retrieved from the database before it is presented to the agent context.
Audit Metadata