Claude Code, Skill
Agentprivacy Skills
Privacy-first AI agent skills for the Agent Skills standard.
Compatibility: Not stated.
Grade C
One Medium finding. Read the findings before installing.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
Rescanned at commit 238024335349, unchanged since the check below.
PERMISSION_SHELL_UNDECLARED
Why this grade
- PERMISSION_SHELL_UNDECLARED Medium
Runs shell commands that the manifest or description does not mention.
role/agentprivacy-lane-chronicle/scripts/citations.py, line 26
raw = subprocess.run(["gh", "pr", "list", "-R", a.repo, "--state", "all", "--search", f"{a.login} in:body,title",
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Concern
requests shell access. No manifest field names shell or command execution.
PERMISSION_SHELL_UNDECLARED
role/agentprivacy-lane-chronicle/scripts/citations.py, line 26
raw = subprocess.run(["gh", "pr", "list", "-R", a.repo, "--state", "all", "--search", f"{a.login} in:body,title",
role/agentprivacy-lane-chronicle/scripts/export_figures.py, line 38
subprocess.run([browser, "--headless=new", "--disable-gpu", "--hide-scrollbars",
role/agentprivacy-lane-chronicle/scripts/render.py, line 49
subprocess.run(common + ["--no-pdf-header-footer", f"--print-to-pdf={pdf}", tmp.as_uri()], check=True, timeout=180)
Show more
role/agentprivacy-lane-chronicle/scripts/render.py, line 52
subprocess.run(common + [f"--force-device-scale-factor={a.scale}", f"--window-size={a.width},{a.max_height}",
Install and update
Pass
No install-time script found, and dependencies are pinned or absent.
Network
Concern
can reach a host that is not written as a fixed address.
NETWORK_NO_FIXED_HOST
wikis/agentprivacy-wiki-page/SKILL.md, line 95
curl -s "http://$DOMAIN/system/sitemap.json" > /dev/null
wikis/agentprivacy-wiki-reindex/SKILL.md, line 43
curl -s "http://$DOMAIN/system/sitemap.json" > /dev/null
wikis/agentprivacy-wiki-sync/SKILL.md, line 151
curl -s -H "Host: <host>.localhost" http://localhost:3030/system/sitemap.json | grep -o '"slug"' | wc -l
Show more
wikis/agentprivacy-wiki-sync/SKILL.md, line 155
curl -s -H "Host: <host>.localhost" http://localhost:3030/system/sitemap.json | grep -oE '"slug":"[^"]+"' | grep -iE "chronicle|draft|plan|audit|candidate|presync|\.bak"
wikis/agentprivacy-wiki-watch/watch.mjs, line 45
const res = await fetch(url, { signal: ctl.signal, headers: { accept: 'application/json' } });
Secrets
Concern
reads a credential or environment file.
SECRETS_PATH_DOTENV
.gitignore, line 28
# Local dev
.gitignore, line 29
.env
agentprivacy-skills-v5/.gitignore, line 28
# Local dev
Show more
agentprivacy-skills-v5/.gitignore, line 29
.env
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Note
a file was over the read cap and was not fully read.
OBFUSCATION_FILE_OVER_READ_CAP
grimoire/city_of_mages_grimoire_v1_4_0.json, line 1
{
grimoire/privacymage_grimoire_v10_2_0.json, line 1
{
Licence
Pass
A licence file is present (LICENSE.md).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit 238024335349. requests shell access. No manifest field names shell or command execution. can reach a host that is not written as a fixed address. reads a credential or environment file. a file was over the read cap and was not fully read.
Date and source
Date checked:
github.com
Commit graded: 2380243353496003e8b0f5e47be2255dc3c764d2
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.