ads-conciencia
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute local Python scripts (
scripts/conciencia.py,scripts/profile.py, andscripts/api/*.py) which manage all campaign registration, check-ins, and data rendering. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes data from external sources and user input.
- Ingestion points: Reads campaign metrics and audit results from
*-audit-results.jsonand~/.claude-ads/history/index.json, and accepts free-text notes from users during check-ins. - Boundary markers: None explicitly defined in the markdown instructions.
- Capability inventory: The skill has the capability to execute shell commands (Bash tool) and write files to the local filesystem.
- Sanitization: The underlying Python scripts perform validation on numeric inputs, but the processing of free-text notes or external JSON values relies on the script logic rather than LLM-level sanitization.
Audit Metadata