ClawAudit verdict
capability-evolver
repo2
Self-described as a 'self-evolution engine' that autonomously writes new code and updates its own memory; defaults to 'Mad Dog Mode' executing changes immediately without review, and exposes an EVOLVE_ALLOW_SELF_MODIFY flag to let the evolver rewrite its own source code — broad autonomous agent-modification capability beyond typical skill scope.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (11)
Possible hardcoded credential
test/sanitize.test.js · prose · downgraded · PASSWORD: "hunter2xyz
Recursive delete from root or home — destructive command
test/skillDistiller.test.js · prose · downgraded · rm -rf /
References child_process — can spawn system processes
scripts/build_public.js · prose · downgraded · child_process
Uses spawn() — can execute external programs
index.js · prose · downgraded · spawn(
Uses exec() — may execute shell commands
src/gep/analyzer.js · prose · downgraded · exec(
Reads files from sensitive system paths
src/gep/deviceId.js · prose · downgraded · readFileSync('/etc
Accesses .ssh directory
test/sanitize.test.js · prose · downgraded · .ssh/
Node http/https module — low-level network access
scripts/publish_public.js · prose · downgraded · require('https')
Accesses sensitive environment variables
scripts/publish_public.js · prose · downgraded · process.env.GITHUB_TOKEN
References agent memory files
src/evolve.js · prose · downgraded · MEMORY.md
Popular HTTP library — network access
test/signals.test.js · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.