p-daily-report

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill reads sensitive local data from the Claude conversation history file. This file contains a log of all interactions, which may include code, keys, or personal information discussed in previous sessions.
  • [COMMAND_EXECUTION]: Utilizes the Bash tool to execute system commands including gh for GitHub access, gws for Google Calendar access, and a local Python script skillctx-resolve.py to manage skill configuration.
  • [DATA_EXFILTRATION]: Fetches activity data from well-known external services including GitHub, Slack, and Google Calendar. These network operations are consistent with the skill's stated purpose of gathering cross-platform activity logs.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources (Slack messages and GitHub PR titles/descriptions) and processes it using the Bash and Write tools.
  • Ingestion points: Reads activity from Slack messages, GitHub contributions, and local Claude history.
  • Boundary markers: Absent. There are no delimiters or instructions provided to the agent to ignore potentially malicious commands embedded in the fetched data.
  • Capability inventory: The skill has access to Bash (shell execution), Write (filesystem modification), and a Python script for updating its own configuration.
  • Sanitization: Absent. The skill does not perform validation or filtering on the content of messages or PR titles before processing them.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 02:44 AM
Security Audit — agent-trust-hub — p-daily-report