dsh-open-dream-rsi@0.4.8
VERIFIED· install onlyPublisher claims: "Let your coding agent dream: strategies must survive counterfactual replay before they earn trust. An offline self-improvement loop over an evolving world model — no fine-tuning, the LLM stays frozen. Speaks MCP. Ships its Python server inside the package" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 86/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
would raise and kill the spawn with ``Exception occurred inFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# soft=0 would insta-kill the child, so skip it.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# rather than kill the spawn.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.except Exception as exc: # never kill the server threadFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# minutes — the 60 s default per-call timeout would kill themFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(cmd, capture_output=True, text=True, timeout=180)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# own session -> own process group we can kill wholesaleFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# low hard rlimit) must not kill the whole cycle.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# (e.g. `npx cursor-openai-api serve` on :3000) — seeFix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for dsh-open-dream-rsi@0.4.8 as of 3d ago. This is the package itself, not its dependencies.