update-claude-md
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data that could potentially contain instructions intended to influence the agent's behavior during the configuration update process.
- Ingestion points: The skill uses
$ARGUMENTSfor user input and@CLAUDE.mdto read the existing configuration file. - Boundary markers: The instructions do not employ specific delimiters or "ignore instructions" warnings to isolate the interpolated data from the core logic.
- Capability inventory: The agent is empowered to read the codebase and write modifications to the
CLAUDE.mdfile. - Sanitization: No validation or escaping mechanism is applied to the input data before it is processed by the agent.
Audit Metadata