autoskill
Analyzes user workflows via screenpipe to propose new skills or compositions based on detected patterns, enhancing productivity.
Install this skill
or
81/100
Security score
The autoskill skill was audited on Jun 3, 2026 and we found 11 security issues across 2 threat categories. Review the findings below before installing.
Categories Tested
Security Issues
low line 106
Access to hidden dotfiles in home directory
SourceSKILL.md
| 106 | ~/.autoskill/proposed/<timestamp>/ (default; override with --out) |
low line 121
Access to hidden dotfiles in home directory
SourceSKILL.md
| 121 | python scripts/autoskill.py promote --proposed ~/.autoskill/proposed/<ts> --skills-dir ../ --name <skill> |
medium line 147
Access to hidden dotfiles in home directory
SourceSKILL.md
| 147 | Proposals land in `~/.autoskill/proposed/<timestamp>/` by default, keeping experimental output out of the skills repo. Pass `--out PATH` to override. |
medium line 161
Access to hidden dotfiles in home directory
SourceSKILL.md
| 161 | Open `~/.autoskill/proposed/<ts>/report.md`, edit drafts in place, delete anything you don't want. Then: |
low line 165
Access to hidden dotfiles in home directory
SourceSKILL.md
| 165 | --proposed ~/.autoskill/proposed/2026-04-17T14-30-00 \ |
low line 9
External URL reference
SourceSKILL.md
| 9 | > **Requires a running [screenpipe](https://github.com/screenpipe/screenpipe) daemon.** This skill has no alternate data source — it reads exclusively from the local screenpipe HTTP API (default `http |
low line 11
External URL reference
SourceSKILL.md
| 11 | > **Network access & environment variables.** This skill makes authenticated HTTP requests to (a) the user's local screenpipe daemon on loopback, and (b) the user-configured LLM backend — one of `http |
low line 31
External URL reference
SourceSKILL.md
| 31 | - **LLM backend defaults to `local`.** The recommended setup is [LM Studio](https://lmstudio.ai/) running `Gemma-4-31B-it` — strong reasoning at a size that fits on most workstation GPUs, and no data |
low line 78
External URL reference
SourceSKILL.md
| 78 | - Install [LM Studio](https://lmstudio.ai/). |
low line 179
External URL reference
SourceSKILL.md
| 179 | endpoint: http://localhost:1234/v1 # LM Studio's Developer server |
low line 183
External URL reference
SourceSKILL.md
| 183 | url: http://localhost:3030 # or https://screenpipe.local via Caddy |
Scanned on Jun 3, 2026
View Security DashboardGitHub Stars 16
Rate this skill
Categorydata analytics
UpdatedJune 15, 2026
charlieviettq/awesome-agent-skill