session-debrief

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell-based operations to interact with the polygraph CLI (e.g., session show, session logs). It utilizes shell parameter expansion (${POLYGRAPH_CLI:-polygraph}) to determine the binary path and uses redirection to manage log files in $TMPDIR.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) because its core functionality involves ingesting and summarizing untrusted data from past session transcripts.
  • Ingestion points: External data enters the agent context via the output of the polygraph session logs command, which is written to a temporary file and subsequently read.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially adversarial commands embedded within the logs.
  • Capability inventory: The agent has the capability to execute CLI commands and spawn subagents with instructions derived from the input data.
  • Sanitization: There is no evidence of sanitization or filtering of the raw log content before it is processed by the agent.- [EXTERNAL_DOWNLOADS]: The skill uses a CLI tool to fetch remote session metadata, transcript logs, and pull request information from external repositories associated with the Polygraph platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 10:13 AM
Security Audit — agent-trust-hub — session-debrief