skill-audience-profiler
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted data including social media comments, private messages, and feedback to build audience profiles, creating a potential vector for malicious instructions to influence the agent.
- Ingestion points: Untrusted data enters the agent context in
SKILL.md(Step 1: '后台数据、评论区反馈、私信咨询') andSKILL.md(Step 6: '从评论区和私信提取'). - Boundary markers: There are no explicit delimiters or instructions provided in the skill to treat harvested comments as untrusted data or to ignore potential commands embedded within them.
- Capability inventory: The skill performs file system write operations in
SKILL.md('保存到 outputs/受众画像/audience-profile.md' and 'profiles//audience.md'). - Sanitization: There is no evidence of sanitization, escaping, or validation of the external content before it is interpolated into the profiling templates in
references/profiling-frameworks.md.
Audit Metadata