search-strategy

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The search strategy workflow involves ingesting and synthesizing information from external sources (chat, wiki, trackers), creating a surface for indirect prompt injection.
  • Ingestion points: Search results from external sources like ~~chat, ~~knowledge base, and ~~project tracker as specified in the query decomposition steps in SKILL.md.
  • Boundary markers: The skill lacks instructions for using delimiters or 'ignore embedded instructions' prompts to isolate retrieved content from the agent's internal instructions.
  • Capability inventory: The skill is configured with run_shell_command and read_file permissions in the frontmatter, which could be exploited if an injection occurs.
  • Sanitization: No sanitization, escaping, or validation logic is provided for external content before it is interpolated into the agent's context for synthesis.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 11:31 PM
Security Audit — agent-trust-hub — search-strategy