specstory-session-summary

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands such as ls, grep, and tail to read and process local session history files located in the .specstory/history/ directory.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting historical session data from .specstory/history/*.md files which may contain instructions from previous interactions. It lacks boundary markers to distinguish content from instructions and does not perform sanitization while maintaining shell execution capabilities.
  • [SAFE]: There is a minor metadata inconsistency where the frontmatter declares an MIT license while the LICENSE.txt file contains the Apache 2.0 license text.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 03:25 AM