Create, read, merge, fill, and secure PDF files.
68
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The prompt shows example CLI invocations and guidance that place passwords directly on the command line (e.g. --user-password/--password) and instructs encrypt/decrypt actions, which requires the agent to insert secret password values verbatim into commands — an insecure pattern.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Required runtime workflow reads outsider-authored free text from user-supplied PDFs via `pdf_read.py --text/--tables/--meta/--fields` using `pdfplumber.extract_text()/extract_tables()` and `pypdf.PdfReader(...).metadata/get_fields()`, so an outsider can submit a poisoned PDF that the skill will ingest without selecting a specific item.
- Repository
- NousResearch/hermes-agent
- Commit
6680afb
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.