ClawAudit verdict
forge-autonomous-agent-v1
High-level description of an autonomous agentic framework with self-mutation and MCP integration; the content is vague marketing copy with no concrete malicious behavior, exfiltration, or code injection present.
⚠ 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.
Findings (7)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
README.md · code · curl -fsSL https://raw.githubusercontent.com/$FORGE_GITHUB_USER/forge/main/insta
Pipe to bash — executes piped content as shell commands
prompts/setup.md · code · | bash
Accesses shell history/config
prompts/setup.md · code · ~/.zshrc
Instructs covert action — may act without user awareness
prompts/setup.md · prose · downgraded · silently
References sudo — requests elevated privileges
prompts/setup.md · prose · downgraded · sudo
apt-get install — installs system packages
prompts/setup.md · prose · downgraded · apt-get install
Popular HTTP library — network access
README.md · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B). 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.
Is this flag fair?
Thanks — recorded.