xy-goal-card
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes a bundled script
scripts/atoms-search.pythat makes network requests tohttps://api.xyskill.xyz. This domain is associated with the skill's vendor and serves as a remote knowledge repository to keep the goal auditing data up to date. - [COMMAND_EXECUTION]: The agent is instructed in
SKILL.mdto execute the local helper scriptatoms-search.pyvia thepython3command. This execution is used to perform searches based on goal keywords and is a legitimate part of the skill's functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied goal descriptions and extracts keywords to query an external knowledge base, representing an ingestion surface for untrusted data.
- Ingestion points: User-provided descriptions of goals, desires, and tasks in the conversation.
- Boundary markers: The instructions do not define specific delimiters for separating the output of the search script from other instructions.
- Capability inventory: The skill has the capability to execute local scripts and perform network operations for data retrieval.
- Sanitization: The prompt instructions mitigate risk by requiring the agent to extract short, specific keywords (2-4 characters) for the search query rather than passing raw user strings.
Audit Metadata