The Agent Skills Directory

[SAFE]: The skill provides structured guidance for product discovery and includes a local utility script to prioritize assumptions. No malicious code, unauthorized network access, or dangerous system modifications were detected.
[INDIRECT_PROMPT_INJECTION]: The scripts/assumption_mapper.py script reads from an external CSV file, which serves as an ingestion point for untrusted data into the agent's context. However, the risk is negligible due to the lack of exploitable capabilities.
Ingestion points: The script reads user-provided data from assumptions.csv or through the --assumption CLI flag in scripts/assumption_mapper.py.
Boundary markers: The script output does not use specific delimiters or instructions to the agent to ignore potentially embedded instructions in the CSV data.
Capability inventory: The skill possesses no network capabilities, file-writing permissions, or arbitrary command execution functions.
Sanitization: The script performs type validation for numerical risk and certainty scores but does not sanitize the assumption statement string content.

product-discovery