attend
Evaluates execution-time risks in AI operations by classifying tasks for risk signals and surfacing findings for user judgment.
Install this skill
or
49/100
Security score
The attend skill was audited on Mar 7, 2026 and we found 5 security issues across 2 threat categories, including 3 high-severity. Review the findings below before installing.
Categories Tested
Security Issues
high line 19
Eval function call - arbitrary code execution
SourceSKILL.md
| 19 | p=Elevated: Eval(t.E) → Fi → Q[AskUserQuestion] → J → A(J, t, Σ) → Σ' |
high line 66
Eval function call - arbitrary code execution
SourceSKILL.md
| 66 | Phase 1: t.E → Eval(t.E) → Fi: Set(Finding) -- risk evaluation [Tool] |
high line 105
Eval function call - arbitrary code execution
SourceSKILL.md
| 105 | Phase 1 Eval (detect) → Read, Grep (evidence gathering; optional) |
low line 85
Access to .env file
SourceSKILL.md
| 85 | SecurityBoundary: $(...) in configs, .env, credential access → Gate |
medium line 204
Access to .env file
SourceSKILL.md
| 204 | | **SecurityBoundary** | `$(...)` in configs, `.env` access, credential patterns | Security violation risk; aligns with boundaries.md secrets rules | |
Scanned on Mar 7, 2026
View Security DashboardInstall this skill with one command
/learn @jongwony/attend