@markjaquith/agency@3.10.2
Manage agentic work across repositories with durable workbases
AI Security Review
scanned 14d ago · by lpm-firewall-aiSource inspection confirms automatic installation of a first party Pi agent extension, which warrants a warning under the agent integration policy. The inspected installer uses ownership checks, and no concrete attack behavior was established.
Decision evidence
public snapshot- The postinstall hook installs a first party extension into the user's Pi agent extensions directory; this is a guarded agent extension lifecycle risk.
- The installer copies the packaged extension only when the destination does not already exist, and updates a file only when its ownership marker and digest match.
- The IntegrationService target inspects project agent configuration paths; its sync behavior is invoked by explicit commands.
- No concrete credential theft, unrelated network exfiltration, destructive behavior, or remote payload execution was identified in the inspected installer and integration paths.
Source & flagged code
10 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@3.10.2.
See all versions of @markjaquith/agency for other recorded verdicts.
- Review the evidence and your use of @markjaquith/agency@3.10.2 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.