build-tcg-deck
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to use
WebSearchandWebFetchto gather meta-game data, tournament results, and tier lists. This introduces a potential surface for indirect prompt injection if an attacker were to poison a TCG-related website with malicious instructions intended to influence the agent's behavior during the deck-building process. - Ingestion points: External data fetched via
WebSearchandWebFetchtools (Step 4). - Boundary markers: None specified in the instructions.
- Capability inventory: Limited to information gathering and natural language processing; the skill does not define dangerous capabilities like file system writes or subprocess execution.
- Sanitization: No explicit sanitization or validation of the fetched web content is performed.
Audit Metadata