series-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: The skill ingests data from user-provided TV series names and summaries in SKILL.md and external content retrieved via the '联网搜索' (Web Search) functionality mentioned in the core functions.
- Boundary markers: There are no explicit instructions to use delimiters or 'ignore instructions' markers within the ingested content to isolate it from the agent's logical flow.
- Capability inventory: The skill is limited to information retrieval and analytical reporting; no dangerous capabilities like file system access, shell execution, or network exfiltration of sensitive local data were found in the provided files.
- Sanitization: The skill instructions do not specify any sanitization, validation, or filtering for external data before it is integrated into the analysis reports.
Audit Metadata