specstory-session-summary

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands, including ls, grep, and tail, to list and extract content from local session history files. These operations are restricted to reading files within the .specstory/history/ directory.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill processes untrusted data from session history files (.specstory/history/*.md). Adversarial content within these files could attempt to influence the agent's summary output.
  • Ingestion points: Markdown history files located in the .specstory/history/ directory (SKILL.md).
  • Boundary markers: The skill instructions specify using _**User**_ and _**Assistant**_ markers to identify message blocks (SKILL.md, session-parsing.md).
  • Capability inventory: Use of shell commands ls, grep, and tail for file discovery and reading (SKILL.md).
  • Sanitization: The instructions do not define specific sanitization or filtering logic for the content extracted from the history files before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:10 PM