speckit-self

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the specify command-line interface to perform administrative tasks such as checking for new releases and upgrading the binary in place.
  • [INDIRECT_PROMPT_INJECTION]: The skill incorporates a surface for potential instruction injection as it directs the agent to read and process output from the specify self command group to determine the availability of updates or preview changes.
  • Ingestion points: The agent is instructed to read output from specify self check and specify self upgrade commands as described in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or specific markers to isolate tool output from the agent's core instructions.
  • Capability inventory: The skill utilizes subprocess execution of the specify CLI for checking and applying updates (SKILL.md).
  • Sanitization: There is no evidence of filtering or sanitization being applied to the command-line output before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 11:50 PM
Security Audit — agent-trust-hub — speckit-self