pre-flight-check
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script
scripts/pre-flight.shwhich uses standard utilities likegrep,find,awk, andwcto analyze project-local files. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local markdown files that may contain externally-sourced content.
- Ingestion points: Processes content from
.learnings/LEARNINGS.md,.learnings/ERRORS.md,.learnings/FEATURE_REQUESTS.md,.learnings/HEALS.md,.evals/EVAL_INDEX.md, and the.context-surfing/directory. - Boundary markers: The automatic hook output uses
<pre-flight-check>XML-style tags to delimit findings, though the manual scan output relies on standard markdown headers. - Capability inventory: The script performs read-only file system operations; however, the skill instructs the agent to act on the discovered patterns, which involves using other tools with broader capabilities (e.g.,
learning-aggregator). - Sanitization: No explicit sanitization or filtering of instructions is performed on the data read from files before it is presented to the agent's context.
Audit Metadata