state of openclaw security

1 in 6 agent skills can read your env vars

Environment variables are where apps keep API keys and tokens, so it's worth knowing which skills can reach them. Check the one you're about to install.

CLAUDE.md.mcp.jsonagent rules
no signup · instant
what we measured
01

Counted from code, not tiers

0.0% can read env vars ≈ 1 in 6
of 19,461 skills
Skills whose code touches process.env, where API keys and tokens live. The broad capability, stated plainly: can read, not does steal.
0.0% read env vars + reach the network ≈ 1 in 10
co-occurrence
Both capabilities present in one skill: the shape of exfiltration, not proof of it. We don't verify the two ever connect.
0.0% touch a credential store ≈ 1 in 179
narrow & real
SSH keys, AWS configs, keychains: the capability that actually means "can read your secrets." We count it separately, on purpose.
the gap is the point
0.0% can read env vars
0.0% can read real secrets

One in 6 can read environment variables. Far fewer can reach real secret stores. Most scanners call all of it credential theft. Conflating the two is how a scanner overstates its own findings, so we don't. You see what the code can do, and exactly how sure we are.

02

Notable in the corpus

The most-flagged skills we've scanned, by capability combination. Not a feed of recent checks, a standing shortlist. Each links to its full verdict.

Browse all 19,461 →
capability ≠ conduct. we say "can," not "will."
counted from code, so prose-only risks aren't here and the real figures run higher.
every number is a measurement, not a verdict.