linkedin-commenter-extractor
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from LinkedIn comments and headlines, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Comment text, headlines, and names are fetched from the Apify actor in 'scripts/extract_commenters.py'.
- Boundary markers: The skill does not provide delimiters or specific instructions to the agent to ignore potentially malicious content within the extracted data.
- Capability inventory: The script is limited to data retrieval and formatting (JSON/CSV). It does not perform file system modifications, arbitrary shell command execution, or network operations outside of the Apify API.
- Sanitization: Extracted comment text is truncated to 500 characters in 'scripts/extract_commenters.py', but the skill does not perform content-based filtering or escaping of the ingested strings.
- [EXTERNAL_DOWNLOADS]: The skill requires the 'requests' Python package and makes network calls to the Apify platform ('api.apify.com') to execute actors and retrieve datasets. These interactions target a well-known automation service and are consistent with the skill's stated purpose.
Audit Metadata