ai-sdk-core

skills-sh:jezweb_claude-skills__ai-sdk-core

View source
C
67/100

First Seen

Feb 18, 2026

Last Scanned

Feb 20, 2026

Findings

3

Score

67/100

CRITICAL 1
MEDIUM 1
LOW 1

Findings (3)

CRITICAL
Fake system prompt
L471

Detects content pretending to be a system prompt

system instruction:
FIX

Remove encoded or obfuscated directives (base64, ROT13, unicode escapes, hex-encoded text). All text should be in plaintext and human-readable.

FP?

Likely FP if the encoded content is legitimate data (e.g., a base64-encoded image, a hex-encoded binary hash) rather than concealed directives.

MEDIUM
Auto-confirm flag bypassing user verification
L550

Detects -y, --yes, or --auto-approve flags in MCP/skill install commands that bypass user confirmation

'-y'
FIX

Remove the -y/--yes auto-confirm flag from MCP server launch arguments. This flag bypasses user confirmation prompts and allows unattended execution of potentially dangerous operations.

FP?

Likely FP if the matched text is an isolated flag (-y or --yes) in documentation describing command-line options, not in an actual MCP config.

LOW
npx auto-install without confirmation
L654

Detects npx with -y flag that bypasses user confirmation for package installation

npx -y 
FIX

Replace npx -y with an explicit npm install step that pins the package to a specific version, then run it. Remove the -y flag to require user confirmation.

FP?

Likely FP if the npx command runs a well-known, trusted tool (e.g., create-react-app) in documentation context with no version pinning concern.