agentcookie-install
Fail
Audited by Snyk on Aug 14, 2026
Risk Level: CRITICAL
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill instructs the operator to read pairing.json (containing a pairing code and pair_url) and then place those secret values verbatim into a pairing command, which requires the LLM/agent to handle and reproduce secrets directly.
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.70). These are downloads of prebuilt agentcookie binaries from a GitHub user's releases page (potential supply‑chain risk — prebuilt executables from a single/unknown repo should be treated as suspicious until verified); the localhost JSON endpoints are benign probes and not a download risk.
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 1.00). This skill explicitly transfers Chrome session cookies from a "source" machine to a "sink" over the network (Tailscale), enables live CDP injection into a remote browser, and instructs creating an empty blocklist (sync-all), all of which intentionally enable credential/session exfiltration and remote session hijacking by agents.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill runs curl/go install at runtime to fetch and install binaries from GitHub (e.g., https://github.com/mvanhorn/agentcookie/releases/download/v1.0.0/agentcookie_1.0.0_darwin_arm64.tar.gz and https://github.com/mvanhorn/agentcookie/releases/download/v1.0.0/agentcookie_1.0.0_linux_amd64.tar.gz and the go install github.com/mvanhorn/agentcookie/cmd/agentcookie@v1.0.0 line), which downloads and executes remote code required for the skill to work.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (high risk: 1.00). The prompt explicitly instructs using sudo to move the agent binary into /usr/local/bin and to install a persistent service (systemd unit), which requires elevated privileges and modifies the host system state.
Issues (5)
W007
HIGHInsecure credential handling detected in skill instructions.
E005
CRITICALSuspicious download URL detected in skill instructions.
E006
CRITICALMalicious code pattern detected in skill scripts.
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata