secure-agent
Enhances AI agent security by enforcing tool restrictions and network egress rules, ensuring compliance with Earl's security protocols.
Install this skill
or
68/100
Security score
The secure-agent skill was audited on Mar 8, 2026 and we found 6 security issues across 3 threat categories, including 1 high-severity. Review the findings below before installing.
Categories Tested
Security Issues
high line 63
Curl to non-GitHub URL
SourceSKILL.md
| 63 | **Note on `Bash(curl *)` and `Bash(wget *)`:** Denying these also blocks all non-API curl |
medium line 115
Curl to non-GitHub URL
SourceSKILL.md
| 115 | curl https://example.com |
medium line 145
Access to hidden dotfiles in home directory
SourceSKILL.md
| 145 | `~/.config/earl/config.toml` (macOS/Linux) or `%APPDATA%\earl\config.toml` (Windows) |
medium line 197
Access to hidden dotfiles in home directory
SourceSKILL.md
| 197 | `~/.config/earl/config.toml` |
low line 64
External URL reference
SourceSKILL.md
| 64 | uses — downloading binaries, health probes (`curl http://localhost:8080/health`), fetching |
low line 115
External URL reference
SourceSKILL.md
| 115 | curl https://example.com |
Scanned on Mar 8, 2026
View Security Dashboard