who-to-contact
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from
gtm/list.jsonandbrand-config.json, which creates a surface for indirect prompt injection.\n - Ingestion points: Reads user-defined signals and titles from
gtm/list.jsonand project settings frombrand-config.json.\n - Boundary markers: None are explicitly defined in the prompt instructions to isolate external data.\n
- Capability inventory: The skill is authorized to write to the
./gtm/directory and execute the localscore.pyscript.\n - Sanitization: The
score.pyscript validates inputs by checking for minimum word counts and filtering out generic persona labels.\n- [COMMAND_EXECUTION]: The skill uses theBashtool to execute a local Python script (score.py) for lead validation. The execution is strictly limited to the script provided within the skill's own directory and does not involve external dependencies or network activity.
Audit Metadata