@markjaquith/agency@3.18.0
Manage agentic work across repositories with durable workbases
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe automatic postinstall performs first-party Pi extension setup, which warrants a warning under the agent integration policy. The inspected source does not establish malicious behavior or a concrete attack surface.
Decision evidence
public snapshot- The package runs an extension installer automatically from its postinstall lifecycle hook.
- The installer copies the package-owned extension into the user's Pi agent extensions directory.
- It skips an existing extension unless its ownership marker and content digest match; uninstall removes only a matching managed extension.
- The inspected integration path identifies project-local Agency and OpenCode configuration locations.
- The flagged process and review services use subprocesses for general process work and Git operations; the inspected snippets show no credential collection or exfiltration.
- The lifecycle hook installs a first-party agent extension without a separate prompt in the installer source.
Source & flagged code
8 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgPackage source references dynamic require/import behavior.
src/utils/interactive-loader.tsView on unpkg · L3Findings
Affected versions and remediation
This report applies to @markjaquith/agency@3.18.0.
See all versions of @markjaquith/agency for other recorded verdicts.
- Review the evidence and your use of @markjaquith/agency@3.18.0 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.