daily-guidance
强制使用：凡是时间尺度在小时及以下的日常行为模拟，必须使用本 Skill 生成、评估、执行和修正每日 Story。
72
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
In `scripts/daily_guidance.py`, the runtime `pre_step`/`command_hook_init` path ingests the lifecycle-hook payload (`ctx.payload` / `--args-json`), and `_build_hook_result` loads `state/daily_guidance/<date>/story.yaml` and then emits `active_segment`/`guidance` derived from that data (so outsider-authored text can affect the agent only if an outsider can submit those hook payloads or the corresponding story.yaml).
- Repository
- tsinghua-fib-lab/AgentSociety
- Commit
1832bcb
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.