agentic-awesome-skills@18.5.0
AAS Core: complete local skill discovery, agent-owned selection, stack validation, and planning, backed by 2,459+ agentic skills.
AI Security Review
scanned 27d ago · by lpm-firewall-aiThe package has a concrete, user-invoked capability to modify AI-agent skill directories, so it warrants a warning under the agent-control policy. Static inspection found no automatic lifecycle trigger or confirmed malicious behavior.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
A user runs the agentic-awesome-skills command without dry-run mode and selects an agent target.
Impact
User-selected agent skill configuration can change; no confirmed covert execution, credential theft, or automatic persistence was found.
Mechanism
The command resolves target directories, clones the package repository, and installs or updates managed skill entries.
AI rationale
The package has a concrete, user-invoked capability to modify AI-agent skill directories, so it warrants a warning under the agent-control policy. Static inspection found no automatic lifecycle trigger or confirmed malicious behavior.
Evidence
tools/bin/install.js
Network endpoints3
github.com/sickn33/agentic-awesome-skills.gitregistry.npmjs.orgapi.apify.com
Decision evidence
public snapshotAI called this Suspicious at 86.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for warning
- The package exposes an installer as its primary command-line entrypoint.
- The installer targets AI-agent skill directories and can create, update, prune, and record managed skill entries.
- Installation occurs only after command-line argument processing and supports a dry-run path.
- The included Apify example sends its supplied service token only to the Apify API.
Evidence against
- The installer can modify external AI-agent skill directories when a user invokes it.
- No npm preinstall, install, or postinstall lifecycle hook was found in package.json.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
10 flagged · loading sourceskills/developer-signup-flow/SKILL.mdView file
165patternName = stripe_test_secret
severity = high
line = 165
High
High Secret
Package contains a high-severity secret pattern.
skills/developer-signup-flow/SKILL.mdView on unpkg · L165165patternName = stripe_test_secret
severity = high
line = 165
High
Secret Pattern
Stripe test secret key in skills/developer-signup-flow/SKILL.md
skills/developer-signup-flow/SKILL.mdView on unpkg · L165tools/bin/aas.jsView file
3L4: const { main } = require("../lib/aas-v1/cli/main");
L5:
Medium
Dynamic Require
Package source references dynamic require/import behavior.
tools/bin/aas.jsView on unpkg · L3Findings
1 Critical6 High6 Medium4 Low
CriticalHardcoded Runtime Data Exfiltrationskills/apify-content-analytics/reference/scripts/run_actor.js
HighHigh Secretskills/developer-signup-flow/SKILL.md
HighCredential Exfiltrationskills/huggingface-tool-builder/references/baseline_hf_api.tsx
HighShips High Entropy Blobskills/theme-factory/theme-showcase.pdf
HighPayload In Excluded Dirskills/fedora-hyprland-installer/tests/test-scripts.sh
HighSemantic Analysis Limitednode_modules/ajv/dist/runtime/parseJson.js#virtual:normalized:round1
HighSecret Patternskills/developer-signup-flow/SKILL.md
MediumDynamic Requiretools/bin/aas.js
MediumNetwork
MediumEnvironment Vars
MediumShips Build Helper
Affected versions and remediation
This report applies to agentic-awesome-skills@18.5.0.
See all versions of agentic-awesome-skills for other recorded verdicts.
- Review the evidence and your use of agentic-awesome-skills@18.5.0 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.