simplywallst

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The skill fetches outsider-authored free text from SimplyWallSt’s API responses (e.g., score.sentence and info.description/CEO name) via runtime HTTP calls to POST /api/grid/filter and GET /api/company{canonical_url}, which are then placed into the agent’s LLM context when the script prints/returns the JSON.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)