The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The script scripts/flomo_local_api.py contains a hardcoded API_SECRET ("dbbc3dd73364b4084c3a69346e0ce2b2") used to generate signatures for API requests.
[CREDENTIALS_UNSAFE]: The find_access_token function in scripts/flomo_local_api.py programmatically extracts the user's access_token by searching through raw LevelDB storage files located in the flomo app's private container path (~/Library/Containers/com.flomoapp.m/Data/Library/Application Support/flomo/Local Storage/leveldb).
[DATA_EXFILTRATION]: The skill reads sensitive authentication material from local application storage and transmits it to the flomoapp.com API.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted text content from flomo memos, creating a surface for indirect prompt injection attacks.
Ingestion points: query and summarize commands in scripts/flomo_local_api.py fetch and process memo content.
Boundary markers: None are present; the agent is not instructed to treat memo content as untrusted data.
Capability inventory: The skill has the ability to perform network requests via the flomo API and write files to the local filesystem using the export-monthly command.
Sanitization: The html_to_markdown function performs basic formatting cleanup but does not sanitize or filter the content for potentially malicious instructions.

flomo-local-api