agent-beacon

Warn

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONPERSISTENCEPRIVILEGE_ESCALATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled Python script (scripts/preflight.py) for integrity checks and runs the beacon CLI for session management and configuration.
  • [DATA_EXFILTRATION]: The skill provides an explicit mechanism to upload session traces to a remote cloud API (beacon share). This is a documented core feature that requires user approval for each share operation.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill reads and processes potentially untrusted content from agent session logs and history files (e.g., runtime.jsonl and history.db described in references/upstream.md) to facilitate trace browsing and memory review.
  • Boundary markers: Instructions in SKILL.md explicitly warn the agent to treat all command output as data and not instructions.
  • Capability inventory: The skill possesses shell command execution capabilities via the bash tool, local file modification via memory skills install, and network egress via the beacon share command as detailed in SKILL.md.
  • Sanitization: The skill recommends manual preview of outgoing payloads and provides a linting tool for lenses to mitigate risks, though it notes that complete browser-based exfiltration cannot be fully prevented in lenses.
  • [PERSISTENCE]: The beacon endpoint install command is used to configure and start system-level background services (such as launchd or systemd) to monitor agent sessions across the host.
  • [PRIVILEGE_ESCALATION]: The installation of background services and management of system-wide configurations (such as those located in /Library/Application Support/ on macOS) may involve or require elevated permissions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 30, 2026, 09:02 AM