@markjaquith/agency@3.6.1
Manage agentic work across repositories with durable workbases
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThis is a real automatic agent-extension lifecycle risk, but the inspected source supports a first-party Agency integration rather than a concrete malicious payload. It should warn rather than block.
Decision evidence
public snapshot- The postinstall hook automatically installs a Pi agent extension.
- The installer copies package code into the user's Pi extensions directory.
- The installed extension hooks agent startup and appends instructions to the system prompt.
- No credential harvesting, data exfiltration, remote payload loading, or self-dependency was found in the inspected lifecycle path.
- The other agent-integration writes are exposed through an explicit `agency integration sync` command.
Source & flagged code
9 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@3.6.1.
See all versions of @markjaquith/agency for other recorded verdicts.
- Review the evidence and your use of @markjaquith/agency@3.6.1 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.