Agent Continuity

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill relies on reading untrusted data from files like .agent/SESSION.md and tasks/todo.md to determine next steps and sanity checks. This creates a vulnerability surface where an attacker with write access to the repository could influence agent behavior.
  • Ingestion points: .agent/SESSION.md, .agent/PROJECT.md, and tasks/todo.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill definition.
  • Capability inventory: The skill expects the agent to execute shell commands (e.g., sanity builds/tests) and perform file system operations based on the state found in these files.
  • Sanitization: There is no requirement for the agent to sanitize or validate the content of the session files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 02:24 PM
Security Audit — agent-trust-hub — Agent Continuity